© 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. 139231
    Prev
    Next
    INDEX
    Explanations

    steal funds, long-term versus, riding area

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

    asking questions and seeking information

    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
    lsulfanyl
    0.50
     Tef
    0.49
     Direkt
    0.48
     پوکر
    0.47
    िज्या
    0.47
     Игорь
    0.47
    Ꮅ
    0.46
    స్తోంది
    0.45
     sărb
    0.45
     Thur
    0.45
    POSITIVE LOGITS
     (\%)
    0.50
    wa
    0.49
    v
    0.49
    uckle
    0.48
    '
    0.48
     habitants
    0.47
    w
    0.46
    boats
    0.45
    ricts
    0.45
    ption
    0.44
    Activations Density 0.000%

    No Known Activations