© 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. 178716
    Prev
    Next
    INDEX
    Explanations

    foods, requirements, or barrel

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

    qualities, volume, games, current, non

    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
     icch
    0.47
    I
    0.47
    나
    0.46
    ッテリー
    0.46
    ندگی
    0.45
     kec
    0.44
     مدیریت
    0.44
    телей
    0.44
    ੁੰ
    0.44
     hydrochloride
    0.43
    POSITIVE LOGITS
    钣
    0.49
    angs
    0.48
     ఒ
    0.46
     olimp
    0.45
    bomb
    0.44
    ROC
    0.44
     আঙ্গ
    0.43
     Auger
    0.43
    切割
    0.43
    exe
    0.42
    Activations Density 0.000%

    No Known Activations