© 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. 151350
    Prev
    Next
    INDEX
    Explanations

    support verbs and prepositions

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

    social, economic, healthcare, career

    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
    ıma
    0.49
     мальчика
    0.49
    ając
    0.47
    द्वी
    0.47
    <unused2168>
    0.47
    ibusdam
    0.46
    akannya
    0.46
     ሂ
    0.45
    າກ
    0.45
    chedelic
    0.44
    POSITIVE LOGITS
     lube
    0.50
    ,
    0.49
     RAIL
    0.45
    8
    0.45
    routine
    0.43
    Situ
    0.43
    leased
    0.43
    level
    0.43
    一座
    0.42
     terrain
    0.42
    Activations Density 0.002%

    No Known Activations