© 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. 249048
    Prev
    Next
    INDEX
    Explanations

    after punctuation, conjunctions, or pronouns

    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
     ఫ్రె
    0.50
    뭘
    0.48
     berjudul
    0.48
     gaman
    0.48
     članak
    0.46
    zina
    0.46
    ينه
    0.45
    லில்
    0.45
     Ztg
    0.45
    मतौर
    0.45
    POSITIVE LOGITS
    Proposal
    0.53
    Promotion
    0.48
    Up
    0.46
    q
    0.46
    Scale
    0.46
    An
    0.45
    ?
    0.45
    Updating
    0.43
    ї
    0.43
    up
    0.43
    Activations Density 0.000%

    No Known Activations