© 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. 129000
    Prev
    Next
    INDEX
    Explanations

    California, then distribute

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

    like or examples

    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
     senaste
    0.43
     Forest
    0.42
     každ
    0.42
    ENDED
    0.42
    Water
    0.42
     mince
    0.42
    欬
    0.42
    ="/">
    0.41
    Kot
    0.41
    aminophen
    0.41
    POSITIVE LOGITS
    った
    0.54
    h
    0.50
     ग्राफ
    0.49
     агре
    0.48
     уравнение
    0.48
    చ్చే
    0.47
    y
    0.47
     CharPtr
    0.46
    VRDR
    0.46
     биз
    0.45
    Activations Density 0.000%

    No Known Activations