© 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. 179457
    Prev
    Next
    INDEX
    Explanations

    wedding and events

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

    how to explanation

    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
    המ
    0.53
    丆
    0.52
     וא
    0.51
    accès
    0.49
    ྭ
    0.48
    扎
    0.46
    门店
    0.46
    ência
    0.46
    iędzy
    0.45
     mengakses
    0.45
    POSITIVE LOGITS
     DJ
    0.50
    cents
    0.49
     Chorus
    0.48
     September
    0.46
     Q
    0.46
     Dj
    0.46
     leaks
    0.46
    lit
    0.44
     Chor
    0.44
    bourne
    0.44
    Activations Density 0.000%

    No Known Activations