© 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. 35960
    Prev
    Next
    INDEX
    Explanations

    Windows Vista

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

    giggles, reasoning, note, rationale

    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
    el
    0.45
    \
    0.43
    拣
    0.43
    来说
    0.43
    ol
    0.42
    本质
    0.42
    zied
    0.42
    d
    0.42
    e
    0.42
    man
    0.42
    POSITIVE LOGITS
     parishes
    0.54
    内の
    0.51
     annexation
    0.51
     rhiz
    0.50
     altitudes
    0.50
     sponsoring
    0.50
     הראשון
    0.50
     chloroform
    0.49
     outcrops
    0.49
     benthic
    0.49
    Activations Density 0.000%

    No Known Activations