© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 139195
    Prev
    Next
    INDEX
    Explanations

    contextual conjunctions and prepositions

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

    building a world

    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
     eriş
    0.49
    STONE
    0.49
     şeyi
    0.48
     devlet
    0.47
    Й
    0.47
     ლი
    0.47
     akses
    0.46
    ト
    0.46
    НИЕ
    0.46
    YEAR
    0.46
    POSITIVE LOGITS
    getUsername
    0.47
     Utils
    0.45
    umat
    0.42
    Reactive
    0.42
     Omaha
    0.41
     придется
    0.40
     gravity
    0.40
     হয়তো
    0.40
     reminded
    0.39
     surprises
    0.39
    Activations Density 0.001%

    No Known Activations