© 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. 227535
    Prev
    Next
    INDEX
    Explanations

    buying tickets for events

    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
    淝
    0.50
    杩
    0.46
    题
    0.45
    兕
    0.45
    igste
    0.44
     एंड्र
    0.43
    Cage
    0.43
    水
    0.42
    寔
    0.42
    ెస్
    0.41
    POSITIVE LOGITS
     INSPE
    0.48
    分散
    0.46
     CHANGES
    0.45
     interfering
    0.45
    merge
    0.44
    bundle
    0.44
     conferencia
    0.44
     abril
    0.44
    f
    0.44
     рассе
    0.44
    Activations Density 0.000%

    No Known Activations