© 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. 169540
    Prev
    Next
    INDEX
    Explanations

    situation not, day till, dog village

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

    list separators

    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
    Ordered
    0.48
    に関しては
    0.46
     manpower
    0.45
    ي
    0.45
     Gastro
    0.44
    ،
    0.43
    ކ
    0.43
    嗥
    0.42
    羅
    0.42
    ال
    0.42
    POSITIVE LOGITS
    munition
    0.48
    ierta
    0.46
    DIRECTORY
    0.44
    dropbox
    0.44
    entingan
    0.44
    ете
    0.44
     मक
    0.44
    tensor
    0.43
     lifegu
    0.43
    niji
    0.43
    Activations Density 0.000%

    No Known Activations