© 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. 145946
    Prev
    Next
    INDEX
    Explanations

    legal basis for

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

    demonstrates result from without

    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
    驅
    0.50
    <unused2200>
    0.48
    Dennis
    0.48
    తు
    0.45
    廢
    0.44
    隐
    0.44
    人
    0.44
    讓
    0.44
    買
    0.44
    彥
    0.43
    POSITIVE LOGITS
     attaining
    0.49
     deducted
    0.48
     thighs
    0.46
    ötzlich
    0.45
     Hyundai
    0.44
     Korea
    0.43
    yyati
    0.43
     kecamatan
    0.43
     creatine
    0.43
     curviliné
    0.43
    Activations Density 0.001%

    No Known Activations