© 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. 231803
    Prev
    Next
    INDEX
    Explanations

    custom or standardized contracts

    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
     ceil
    0.50
     khán
    0.49
    ن
    0.49
     pły
    0.49
     supergiants
    0.49
     autres
    0.48
     arabe
    0.48
     arab
    0.47
     conseil
    0.47
     chiếm
    0.47
    POSITIVE LOGITS
    ks
    0.52
    lista
    0.51
    AMP
    0.48
    gat
    0.47
    <0xBC>
    0.47
    ixels
    0.45
    serialized
    0.44
    ASP
    0.44
    rigid
    0.44
    ORT
    0.43
    Activations Density 0.000%

    No Known Activations