© 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. 143950
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases

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

    languages, avoiding issues, series, older, sorting

    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
    '
    0.50
     an
    0.47
    ’
    0.46
     facilitates
    0.45
     adequado
    0.44
     añadido
    0.44
     balances
    0.42
     द
    0.42
     einem
    0.42
     outweighs
    0.41
    POSITIVE LOGITS
    áték
    0.43
    赓
    0.42
    ங்
    0.42
    ကြည့်
    0.42
    缫
    0.41
     الكهربائيه
    0.40
     மிசோரம்
    0.40
    踌
    0.40
    chia
    0.40
    endregion
    0.40
    Activations Density 0.000%

    No Known Activations