© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111722
    Prev
    Next
    INDEX
    Explanations

    yes followed by descriptors

    np_acts-logits-general · gemini-2.5-flash-lite

    affirmative responses at the beginning of answers (like "Yes," "That's," or "It is").

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    affirmative responses or confirmations, particularly "yes" and "that" in conversational contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     دیگر
    -1.48
    richtig
    -1.46
    Não
    -1.45
    Ông
    -1.43
     إذا
    -1.43
    drucks
    -1.42
    ladung
    -1.41
    Vlast
    -1.38
    tauchen
    -1.38
    ınıza
    -1.37
    POSITIVE LOGITS
     surprising
    1.71
    se
    1.60
     used
    1.52
    </
    1.51
     how
    1.46
     help
    1.46
    当時は
    1.44
    全く
    1.43
     characteristics
    1.42
     -"
    1.42
    Activations Density 0.015%

    No Known Activations