© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 116050
    Prev
    Next
    INDEX
    Explanations

    King, God, awesome, drums, press

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

    right to

    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
     RT
    0.50
     Ray
    0.48
     MP
    0.46
    </h2>
    0.46
     ekran
    0.46
     OTS
    0.46
     olacaktır
    0.45
     Jean
    0.44
     alta
    0.44
    :
    0.44
    POSITIVE LOGITS
    ゲット
    0.56
    スン
    0.53
    NAMEN
    0.51
    NUM
    0.51
     রাজশাহ
    0.51
     রাজশাহী
    0.50
     タイプ
    0.48
    leValue
    0.46
    glRaster
    0.46
    getAddress
    0.46
    Activations Density 0.000%

    No Known Activations