© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 4962
    Prev
    Next
    INDEX
    Explanations

    Welsh place names and language

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

    missing children resources

    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
     ٹینس
    0.42
    😧
    0.39
     дово
    0.38
    許
    0.38
    >-->
    0.37
    😍😍
    0.37
     マル
    0.36
     않는
    0.36
     mandates
    0.35
    ونات
    0.35
    POSITIVE LOGITS
     Cym
    0.94
    wydd
    0.86
     cym
    0.80
    ydd
    0.77
     gyda
    0.76
    wyr
    0.75
     yn
    0.75
     ym
    0.75
     hefyd
    0.74
     Yn
    0.73
    Activations Density 0.034%

    No Known Activations