© 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. 26317
    Prev
    Next
    INDEX
    Explanations

    carrying items in bags

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

    pipeline operator ` or `Mid` `conventionally`

    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
     was
    0.50
     built
    0.45
     goals
    0.43
     Built
    0.43
     цели
    0.42
    1
    0.41
    吋
    0.40
    фта
    0.40
     activities
    0.39
     Фото
    0.39
    POSITIVE LOGITS
    💣
    0.59
    🎀
    0.53
    UIServer
    0.52
    🍷
    0.49
    <unused74>
    0.47
    👔
    0.47
    /*',
    0.47
     หาก
    0.46
    ♋
    0.46
    🎐
    0.46
    Activations Density 0.000%

    No Known Activations