© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7053
    Prev
    Next
    INDEX
    Explanations

    code output and declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    적
    0.72
    객
    0.63
     NULL
    0.60
    }):
    0.60
    가지
    0.59
     prop
    0.59
    비
    0.56
    стви
    0.55
    oux
    0.54
    
    0.54
    POSITIVE LOGITS
    ("\(
    0.98
    !..
    0.98
    ilihan
    0.96
     "\(
    0.95
     Biennale
    0.92
    xcodep
    0.90
     myös
    0.89
    Equatable
    0.86
    ótica
    0.86
    ForEach
    0.85
    Activations Density 0.035%

    No Known Activations