© 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. 182152
    Prev
    Next
    INDEX
    Explanations

    browse through

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

    branching from or off

    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
     IS
    0.47
     logiciels
    0.47
     nombr
    0.44
     ""`
    0.43
     designates
    0.42
     अटे
    0.42
     NOTHING
    0.42
     Recherche
    0.41
     dey
    0.41
    ⠿
    0.40
    POSITIVE LOGITS
    erol
    0.51
    جموع
    0.50
    從小
    0.49
    eryllium
    0.49
    दृ
    0.48
    ૩
    0.48
    ህል
    0.47
     Snapshot
    0.47
     steeply
    0.46
     طويلة
    0.46
    Activations Density 0.001%

    No Known Activations