© 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. 13391
    Prev
    Next
    INDEX
    Explanations

    drawdown, drywall, what there, and Paul

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

    if i recall

    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
     U
    0.48
     Label
    0.47
     Fellow
    0.47
    uka
    0.46
    anda
    0.44
     pré
    0.42
    agi
    0.42
     Nr
    0.41
     Earl
    0.40
     Place
    0.40
    POSITIVE LOGITS
    ୍କ
    0.55
    찜
    0.51
    бие
    0.50
    ނ
    0.49
    っており
    0.49
    予測
    0.49
    heuristic
    0.49
    wci
    0.48
    觜
    0.48
    慘
    0.48
    Activations Density 0.000%

    No Known Activations