© 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. 30631
    Prev
    Next
    INDEX
    Explanations

    safe and, mobile, king bed, being transformed, equipment

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

    something first important potential universe

    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
    на
    0.53
     carriage
    0.52
    с
    0.48
     Carta
    0.46
     car
    0.45
     say
    0.45
     regime
    0.45
     constrained
    0.45
     pula
    0.44
    Carta
    0.43
    POSITIVE LOGITS
    bles
    0.62
    كر
    0.57
    喡
    0.57
    𝙊
    0.55
     ক্যান্স
    0.53
    ⨔
    0.52
    𝙡
    0.51
    كي
    0.51
     कैंसर
    0.50
    HIV
    0.50
    Activations Density 0.000%

    No Known Activations