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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10299
    Prev
    Next
    INDEX
    Explanations

    stimulus response consisted

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

    scientific terms related to research stimuli and responses in experimental contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     possib
    -1.59
    2
    -1.57
    也
    -1.55
    也是
    -1.49
    也在
    -1.47
     vogel
    -1.43
     eene
    -1.40
    毟
    -1.39
    也不
    -1.38
     hecta
    -1.35
    POSITIVE LOGITS
     but
    1.66
     ALL
    1.51
     both
    1.51
    珦
    1.49
    юрпри
    1.49
     than
    1.46
    providedIn
    1.44
    товых
    1.44
     meget
    1.42
    izace
    1.42
    Activations Density 0.001%

    No Known Activations