© 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. 129324
    Prev
    Next
    INDEX
    Explanations

    time released

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

    control, stated, recommended, handle, legal

    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
     हिस्से
    0.54
     huidige
    0.53
     directe
    0.53
     እንቅ
    0.52
     homenagem
    0.52
     मौजूदा
    0.50
    こだわ
    0.50
    <unused597>
    0.50
     všet
    0.50
     politiques
    0.50
    POSITIVE LOGITS
     farmers
    0.46
     in
    0.44
     Release
    0.42
     wen
    0.42
    #,
    0.42
    itioner
    0.41
    ABC
    0.41
     Minimum
    0.41
    JD
    0.40
    Wer
    0.40
    Activations Density 0.001%

    No Known Activations