© 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. 245138
    Prev
    Next
    INDEX
    Explanations

    trekking reservations modern material

    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
    changed
    0.54
    <0x80>
    0.52
    opened
    0.52
    financial
    0.47
    shifted
    0.47
    up
    0.46
    <0x9A>
    0.46
    ਲੀ
    0.45
    changing
    0.45
    open
    0.45
    POSITIVE LOGITS
     மற்ற
    0.48
     منی
    0.46
     sporty
    0.45
     ț
    0.45
     άλλ
    0.43
     செய்யும்
    0.42
     جلد
    0.42
     vườn
    0.42
    钳
    0.42
     Vegetation
    0.42
    Activations Density 0.001%

    No Known Activations