© 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. 89647
    Prev
    Next
    INDEX
    Explanations

    modal verbs and dependent clauses

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

    >be me,

    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
    Price
    0.42
    اة
    0.42
     kurze
    0.42
     symbolName
    0.42
     값
    0.41
     Matte
    0.41
     moeilijk
    0.41
     stupe
    0.41
     nimi
    0.40
     Meesho
    0.40
    POSITIVE LOGITS
     поскольку
    0.51
     nossa
    0.50
     может
    0.48
    льность
    0.47
     cuyo
    0.47
    тах
    0.47
     оюн
    0.47
    $',
    0.47
    orada
    0.47
    america
    0.46
    Activations Density 0.001%

    No Known Activations