© 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. 30820
    Prev
    Next
    INDEX
    Explanations

    WomensJobListtrue substancedesigns

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

    man named Silas

    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
    t
    0.48
     rides
    0.46
     crushes
    0.44
     exudes
    0.44
     fares
    0.43
    你好
    0.43
    攔
    0.43
    asers
    0.42
     picnics
    0.42
     trăm
    0.42
    POSITIVE LOGITS
     დ
    0.48
     persönlichen
    0.48
    ěst
    0.48
     ምስ
    0.47
    łego
    0.46
     personnelle
    0.45
     لی
    0.45
     personale
    0.45
     nivel
    0.45
     казіно
    0.44
    Activations Density 0.000%

    No Known Activations