© 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. 51498
    Prev
    Next
    INDEX
    Explanations

    **connects text or ideas

    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
     ramas
    0.49
    drums
    0.48
    planned
    0.46
     quail
    0.46
    ^{*}$-
    0.46
    targeted
    0.46
    burden
    0.46
     carin
    0.46
    healthy
    0.45
    勸
    0.44
    POSITIVE LOGITS
     notamment
    0.50
     Assignment
    0.49
     Nervous
    0.49
     Mixture
    0.49
     Nerv
    0.48
     Duration
    0.48
     Departure
    0.48
     Substitution
    0.48
     两
    0.47
     Alipay
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.