© 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. 8191
    Prev
    Next
    INDEX
    Explanations

    mentions and replies

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

    describing relationships or circumstances

    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
     ቡ
    0.39
     avions
    0.39
    refreshToken
    0.39
     stressful
    0.39
     により
    0.39
     oub
    0.38
    ჷ
    0.37
     spie
    0.37
    窟
    0.37
    笼
    0.36
    POSITIVE LOGITS
    ered
    0.47
     gesagt
    0.46
    myer
    0.44
    bat
    0.44
    heat
    0.44
    professor
    0.44
    cattle
    0.43
     Decay
    0.43
     കരു
    0.41
     lieutenant
    0.40
    Activations Density 0.000%

    No Known Activations