© 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. 181589
    Prev
    Next
    INDEX
    Explanations

    object + type or descriptor

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

    field-specific vocabulary

    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
    ｻ
    0.47
     istedi
    0.47
     mieli
    0.46
    اكم
    0.45
     Cadd
    0.45
    țion
    0.44
     Communion
    0.44
     Sands
    0.44
     bilater
    0.44
     সমাবে
    0.43
    POSITIVE LOGITS
    бом
    0.46
     म्हणा
    0.46
     their
    0.44
     디
    0.43
     disillusion
    0.42
     상관
    0.41
     reve
    0.41
    their
    0.41
    ете
    0.40
    UIColor
    0.40
    Activations Density 0.000%

    No Known Activations