© 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. 39209
    Prev
    Next
    INDEX
    Explanations

    fa, col, state, comm, src

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

    CSS utility classes with hyphens

    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
     siguientes
    0.46
    ैट
    0.46
    ૂત
    0.42
    :
    0.41
    ח
    0.41
    արկ
    0.40
    ută
    0.40
    觞
    0.40
     poudre
    0.39
    रिस
    0.39
    POSITIVE LOGITS
    -
    0.54
    -(
    0.44
    -,
    0.44
    -${
    0.43
    -{
    0.41
    ־
    0.41
    $-
    0.40
    -%
    0.40
    -\\
    0.39
     ඔහු
    0.39
    Activations Density 0.000%

    No Known Activations