© 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. 115002
    Prev
    Next
    INDEX
    Explanations

    even though

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

    provide a

    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
    t
    0.59
    g
    0.59
    in
    0.56
    </b>
    0.55
    al
    0.54
    -
    0.54
    \[
    0.53
    p
    0.53
    </strong>
    0.52
    n
    0.52
    POSITIVE LOGITS
     getSchema
    0.50
    CameraController
    0.50
     గుర్త
    0.49
     applicator
    0.48
     vectorstock
    0.48
     myCamera
    0.48
    ᓲ
    0.48
     بچ
    0.47
     voisines
    0.47
    getField
    0.47
    Activations Density 0.000%

    No Known Activations