© 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. 112224
    Prev
    Next
    INDEX
    Explanations

    allows easy, disable WIFI, for Permits

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

    hardware description language

    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
    korn
    0.48
    ';",
    0.47
    🫢
    0.46
    溜
    0.45
    worked
    0.44
    🥹
    0.43
     Alice
    0.42
     끝
    0.42
    teis
    0.42
     </
    0.42
    POSITIVE LOGITS
    FIELDS
    0.50
    REFERENCE
    0.48
    APPRO
    0.47
    ulares
    0.46
    abilità
    0.46
     στό
    0.45
    RAM
    0.44
    ug
    0.43
    reeks
    0.43
    Structure
    0.42
    Activations Density 0.000%

    No Known Activations