© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 39554
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by quantity or word

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

    closing parenthesis and operators

    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
    🦎
    0.51
    anza
    0.51
     vignettes
    0.47
    শিয়া
    0.46
    랐
    0.46
    avila
    0.46
    riften
    0.46
    жна
    0.45
     مدينه
    0.44
    olla
    0.43
    POSITIVE LOGITS
     U
    0.50
    cps
    0.50
     M
    0.49
     Philippine
    0.49
     S
    0.48
     Bees
    0.46
     Wh
    0.45
     Př
    0.44
     След
    0.44
     periods
    0.44
    Activations Density 0.006%

    No Known Activations