© 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. 63002
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs

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

    infinitive verb phrases

    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
    لان
    0.60
     مين
    0.57
    ه
    0.57
     گا۔
    0.54
     представлена
    0.54
    ﺻ
    0.53
     livres
    0.53
     Wanneer
    0.53
    اني
    0.52
     براي
    0.52
    POSITIVE LOGITS
     have
    1.02
     be
    0.95
    pple
    0.88
    지
    0.80
    ash
    0.73
     allow
    0.71
    ffee
    0.70
    have
    0.70
     ask
    0.68
    ppled
    0.68
    Activations Density 0.113%

    No Known Activations