© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 73110
    Prev
    Next
    INDEX
    Explanations

    special words in list descriptions

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

    ability to, used to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     flirt
    0.53
    /
    0.47
    <0x0D>
    0.44
    ۰۰
    0.44
    Flair
    0.44
    Photograph
    0.44
     ADR
    0.44
     (
    0.43
     Guidance
    0.43
     Argument
    0.43
    POSITIVE LOGITS
    覺
    0.54
    衞
    0.49
    )}{\
    0.45
     بالٹ
    0.44
    樓
    0.44
     করিতাম
    0.43
     இழு
    0.43
    <unused10>
    0.43
    ត្
    0.43
    道の
    0.43
    Activations Density 0.000%

    No Known Activations