© 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. 4680
    Prev
    Next
    INDEX
    Explanations

    scoring goals

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

    score and scoring

    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
    Orders
    0.41
    龐
    0.40
     കാലാവ
    0.40
    ensibly
    0.39
    ผ้า
    0.38
    Survey
    0.38
     распростра
    0.38
    keyword
    0.37
     SURVEY
    0.37
    경
    0.37
    POSITIVE LOGITS
     scoring
    2.50
     scored
    2.36
    scoring
    2.25
     Scoring
    2.25
     scorer
    2.16
     scorers
    2.16
    scored
    2.11
     score
    1.91
    scorer
    1.78
    score
    1.69
    Activations Density 0.113%

    No Known Activations