© 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. 17616
    Prev
    Next
    INDEX
    Explanations

    giving approval or go-ahead

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

    approval and permission

    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
    pett
    0.41
    ಿಕೊಳ್ಳ
    0.36
    庴
    0.36
    Submitted
    0.35
     ক্রমশ
    0.35
    ടൊപ്പം
    0.35
    \{-\
    0.34
    Identify
    0.34
     உண்மைய
    0.34
     elaborate
    0.33
    POSITIVE LOGITS
     green
    1.79
     nod
    1.72
     зелены
    1.60
    green
    1.54
    绿
    1.49
     groene
    1.48
    綠
    1.45
     thumbs
    1.44
     nods
    1.43
     go
    1.41
    Activations Density 0.083%

    No Known Activations