© 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. 4764
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and parentheses

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

    min, max, avg, sum, fibonacci

    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
    plaat
    0.43
    चाप
    0.42
    became
    0.41
    enskap
    0.40
    ঋ
    0.40
    czak
    0.40
    fohlen
    0.39
    null
    0.39
    कों
    0.38
    ittää
    0.38
    POSITIVE LOGITS
     (!
    0.66
     ((
    0.63
     (+
    0.56
     (-
    0.55
     (
    0.54
     ((*
    0.53
     (((
    0.51
    ...+
    0.50
    /+
    0.50
     (~
    0.50
    Activations Density 0.014%

    No Known Activations