© 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. 38319
    Prev
    Next
    INDEX
    Explanations

    legal claims involving drunk, welcome on these, latest revisions, back court

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

    What if, why

    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
     Recherches
    0.50
     Leistungs
    0.50
     nämlich
    0.49
     മത്സ്യ
    0.49
     S
    0.47
     Phi
    0.46
     Chung
    0.46
     Kond
    0.46
     Obwohl
    0.45
     którzy
    0.45
    POSITIVE LOGITS
     стабили
    0.46
    दाय
    0.46
     बटा
    0.46
     לו
    0.45
     فعل
    0.45
    シオ
    0.44
    󠁮
    0.44
     spad
    0.44
    omania
    0.44
    вах
    0.43
    Activations Density 0.000%

    No Known Activations