© 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. 1986
    Prev
    Next
    INDEX
    Explanations

    specific indices

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

    numerical indices

    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
    Captain
    0.42
    Liam
    0.42
     Manor
    0.41
     ਸੁ
    0.41
    туу
    0.41
     लॉर्ड
    0.41
     Captain
    0.40
    🎂
    0.40
     Liam
    0.40
     নামাজ
    0.39
    POSITIVE LOGITS
     index
    4.78
     Index
    4.56
    index
    4.47
     indexes
    4.31
     индекс
    4.28
     INDEX
    4.25
     indeks
    4.25
    Index
    4.22
     indices
    4.06
    INDEX
    4.03
    Activations Density 0.127%

    No Known Activations