© 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. 110597
    Prev
    Next
    INDEX
    Explanations

    availability, contracts, conditions

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

    if caught, reputational damage

    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
    as
    0.55
     encuentre
    0.53
     cinco
    0.52
    й
    0.50
    qué
    0.50
    aj
    0.49
    كه
    0.48
    at
    0.48
     აქ
    0.48
     sirven
    0.48
    POSITIVE LOGITS
     compressibility
    0.46
     Premises
    0.46
     premiums
    0.43
     spectators
    0.43
    蚣
    0.43
     conditionals
    0.43
     classifiers
    0.42
     impurities
    0.41
     लिह
    0.41
    hauer
    0.41
    Activations Density 0.001%

    No Known Activations