© 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. 146172
    Prev
    Next
    INDEX
    Explanations

    bloodshed, Genevieve, link hospital, flags

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

    limited features, difficult, anomaly

    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
    imgInit
    0.45
    恴
    0.45
    صوص
    0.45
     Palazzo
    0.45
    зыва
    0.45
    㐫
    0.44
     Einführung
    0.44
     الاح
    0.43
    閉じ
    0.43
    頼
    0.43
    POSITIVE LOGITS
    d
    0.70
    i
    0.66
    m
    0.62
    c
    0.56
    M
    0.55
    k
    0.54
    ্রেট
    0.52
     simplest
    0.51
     normals
    0.51
     techniques
    0.50
    Activations Density 0.001%

    No Known Activations