© 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. 182121
    Prev
    Next
    INDEX
    Explanations

    donated money, event listeners, claims

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

    creating videos

    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
     ಅಭಿ
    0.47
    鯰
    0.46
    Pinterest
    0.46
    炼
    0.44
    衝突
    0.43
    ку
    0.43
     Матери
    0.43
    <0x10>
    0.42
    rarr
    0.42
    r
    0.42
    POSITIVE LOGITS
     mythology
    0.59
    ගත්
    0.48
     topography
    0.47
     endurance
    0.46
     modernize
    0.46
     extraordinaire
    0.45
     placeholders
    0.45
     revitalization
    0.45
     mythological
    0.45
     substitution
    0.44
    Activations Density 0.001%

    No Known Activations