© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113079
    Prev
    Next
    INDEX
    Explanations

    Ruby `has_many` associations

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

    quotation marks that begin string literals or attribute values in code.

    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
    坝
    -1.45
    thinkable
    -1.44
    Unfortunately
    -1.43
     """
    -1.41
     ...
    -1.41
     masterpiece
    -1.41
     It
    -1.39
     ●
    -1.38
    should
    -1.38
     должны
    -1.34
    POSITIVE LOGITS
     Warszawie
    1.41
     recomiendo
    1.41
    ⃤
    1.39
    argest
    1.38
     calitate
    1.32
    ēja
    1.29
    🪬
    1.26
     enten
    1.26
     that
    1.23
     grze
    1.22
    Activations Density 0.002%

    No Known Activations