© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4653
    Prev
    Next
    INDEX
    Explanations

    out + prepositions/adverbs

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

    outputting code, data, or results

    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_53_width_65k_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
     Außen
    0.59
    из
    0.57
    outside
    0.53
    Outside
    0.52
     வெளியில்
    0.52
    ออก
    0.51
    출
    0.51
    出來
    0.50
     luar
    0.48
    İ
    0.47
    POSITIVE LOGITS
    ting
    0.58
    loud
    0.58
     loud
    0.56
    rages
    0.55
    ters
    0.52
    ubers
    0.52
    skirts
    0.52
    selves
    0.50
    laws
    0.49
    uliers
    0.49
    Activations Density 0.174%

    No Known Activations