© 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. 201047
    Prev
    Next
    INDEX
    Explanations

    title and names

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

    radioactive dating

    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
    イルス
    0.50
    奎
    0.49
    董事
    0.48
     disponibil
    0.48
    拒
    0.47
    局
    0.45
    南海
    0.45
    乗
    0.43
    师傅
    0.43
    揆
    0.43
    POSITIVE LOGITS
    alakip
    0.48
     setTitle
    0.47
    alpha
    0.47
     title
    0.46
    zeige
    0.45
    andid
    0.44
     TITLE
    0.43
    allic
    0.43
    ificación
    0.43
    arras
    0.43
    Activations Density 0.000%

    No Known Activations