© 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. 44014
    Prev
    Next
    INDEX
    Explanations

    numbers and minutes

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

    frequency, recall, format, €

    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
     on
    0.46
    وانه
    0.45
    chandise
    0.43
     Convergence
    0.42
     bekannte
    0.42
    ت
    0.42
     الجرس
    0.42
     على
    0.41
     broke
    0.41
     tief
    0.41
    POSITIVE LOGITS
     `:`,
    0.53
    ❌
    0.49
    ⛔
    0.49
    🟡
    0.49
    ➡️
    0.46
    鞣
    0.46
    புது
    0.46
    😅
    0.45
    ₂,
    0.45
    🫶
    0.44
    Activations Density 0.000%

    No Known Activations