© 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. 69789
    Prev
    Next
    INDEX
    Explanations

    actions or temporal sequences

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

    specific descriptors

    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
    G
    0.47
    _
    0.47
    il
    0.46
    ής
    0.43
    Campo
    0.43
    o
    0.42
    -
    0.42
    ），
    0.41
    pportunities
    0.41
    facebook
    0.41
    POSITIVE LOGITS
     variar
    0.54
     varier
    0.54
     tumeur
    0.53
     unavoid
    0.50
     videre
    0.50
     venant
    0.48
     obicei
    0.47
    ه
    0.47
     plafond
    0.46
     vidi
    0.46
    Activations Density 0.000%

    No Known Activations