© 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. 126499
    Prev
    Next
    INDEX
    Explanations

    elections or official proceedings

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

    current context probability

    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
    Kenya
    0.53
    ק
    0.50
    FromName
    0.45
    Caribbean
    0.45
     मम
    0.43
     때는
    0.42
     Kenya
    0.41
    一
    0.41
     moneys
    0.41
     acid
    0.40
    POSITIVE LOGITS
    Declar
    0.49
     ballots
    0.47
     tweets
    0.46
     tailles
    0.45
     Declar
    0.45
     candidats
    0.44
    يرين
    0.43
     ouvert
    0.43
     Schre
    0.42
     valide
    0.42
    Activations Density 0.000%

    No Known Activations