© 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. 116405
    Prev
    Next
    INDEX
    Explanations

    advice and information

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

    DynamoDB Partition Key

    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
    rt
    0.51
    є
    0.49
    OW
    0.47
    alkeeper
    0.46
    she
    0.46
    ASA
    0.46
    eta
    0.45
    A
    0.44
    agina
    0.44
    ian
    0.44
    POSITIVE LOGITS
    蜼
    0.52
     détour
    0.49
     suffit
    0.49
     tyre
    0.49
    炇
    0.47
     tyres
    0.46
    ⌄
    0.46
     मजेदार
    0.46
    <unused44>
    0.46
     хвата
    0.46
    Activations Density 0.001%

    No Known Activations