© 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. 181383
    Prev
    Next
    INDEX
    Explanations

    free time and rights

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

    Northeast US weather events

    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
    to
    0.56
     spans
    0.53
    td
    0.52
    lfloor
    0.50
    mination
    0.47
    m
    0.47
    、
    0.47
    rangle
    0.46
     regulates
    0.46
    lo
    0.45
    POSITIVE LOGITS
     друз
    0.52
    OrDefault
    0.50
     Muk
    0.46
    썸
    0.46
     vay
    0.45
     немає
    0.44
     improb
    0.44
     เก็
    0.44
     monet
    0.42
    ReturnType
    0.42
    Activations Density 0.002%

    No Known Activations