© 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. 106571
    Prev
    Next
    INDEX
    Explanations

    only scratched the surface

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

    Affirmation, comparison, knowledge

    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
    Introduction
    0.59
    ה
    0.52
    ย
    0.52
    ስታ
    0.49
    ท
    0.48
    0.48
    Continuing
    0.47
    Language
    0.46
    www
    0.46
    Supported
    0.46
    POSITIVE LOGITS
     مند
    0.57
    etchup
    0.54
    一块
    0.54
    ږئ
    0.51
    ']))->
    0.48
     vài
    0.48
     Cenomanian
    0.47
    ামুটি
    0.47
    会有
    0.47
     قیام
    0.47
    Activations Density 0.000%

    No Known Activations