© 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. 8310
    Prev
    Next
    INDEX
    Explanations

    occurrence

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

    count occurrences

    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
    粡
    0.42
    ಜ್ಞ
    0.38
     dakkh
    0.37
     unimaginable
    0.36
     ప్రశ్న
    0.36
    വന
    0.36
    ennzeichnet
    0.36
    ቑ
    0.36
     क्षमता
    0.36
     बबलू
    0.36
    POSITIVE LOGITS
     occurrence
    3.80
     Occurrence
    3.52
    occurrence
    3.38
     occurrences
    3.36
    Occurrence
    3.30
     incidence
    2.70
    発生
    2.63
    occur
    2.63
     발생
    2.53
     ocurren
    2.48
    Activations Density 0.063%

    No Known Activations