© 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. 88967
    Prev
    Next
    INDEX
    Explanations

    constantly immediately

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

    sports recruiting

    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
     deven
    0.58
    Registre
    0.55
    IUS
    0.51
    <0x0D>
    0.50
    regist
    0.47
    nj
    0.47
    쇤
    0.47
    YU
    0.46
    become
    0.46
     Međ
    0.46
    POSITIVE LOGITS
     tight
    0.46
     recruiting
    0.46
     lanes
    0.46
     दीक्षित
    0.46
     drilling
    0.45
     حسین
    0.45
     shirts
    0.45
     زیاد
    0.45
     away
    0.44
     recruits
    0.43
    Activations Density 0.001%

    No Known Activations