© 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. 17291
    Prev
    Next
    INDEX
    Explanations

    conjunctions and separators

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

    lists or enumeration

    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
     plays
    0.45
     heritage
    0.44
     versus
    0.37
     explored
    0.36
     ಸೇರಿದ
    0.36
    versus
    0.36
    与此同时
    0.33
    <unused2197>
    0.33
     hanging
    0.33
    ieval
    0.33
    POSITIVE LOGITS
    및
    1.16
    /
    1.14
    および
    1.13
     एवं
    1.11
    และ
    1.10
     및
    1.02
    及び
    1.01
     ও
    0.95
    及
    0.95
    ＆
    0.94
    Activations Density 0.000%

    No Known Activations