© 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. 73678
    Prev
    Next
    INDEX
    Explanations

    designing, previous, closing, products

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

    design patterns and principles

    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
     кото
    0.46
     getWeather
    0.46
    getRedTeam
    0.45
    㴓
    0.45
    愘
    0.44
     വിദ്യാഭ്യാസ
    0.44
    㴼
    0.44
    鱻
    0.43
    培养
    0.43
     jackets
    0.42
    POSITIVE LOGITS
    ότε
    0.46
     cellulaire
    0.46
    ὸ
    0.44
    ນາ
    0.43
     desapare
    0.42
    TableModel
    0.42
    oggling
    0.42
     way
    0.41
    (
    0.41
    etime
    0.40
    Activations Density 0.001%

    No Known Activations