© 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. 159580
    Prev
    Next
    INDEX
    Explanations

    public delivered county refunds country disk

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

    finding locations or information

    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
    يا
    0.55
    十五
    0.54
     برق
    0.54
    KeyDown
    0.50
    刹
    0.50
    ذج
    0.49
    ʇ
    0.48
    waitUntil
    0.47
    folios
    0.47
    十三
    0.46
    POSITIVE LOGITS
     deposition
    0.46
     playing
    0.46
     fee
    0.45
     devem
    0.45
     hitting
    0.45
     deve
    0.44
     definitive
    0.44
     dining
    0.43
     필
    0.43
     must
    0.42
    Activations Density 0.000%

    No Known Activations