© 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-65K
    7. 4850
    Prev
    Next
    INDEX
    Explanations

    concept release website graduate

    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_65k_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
     longues
    1.05
     incidents
    1.05
     miRNAs
    1.00
     essere
    1.00
     hearings
    0.97
    ↵↵↵↵
    0.96
     concerns
    0.95
    nici
    0.93
     delegates
    0.92
    能
    0.91
    POSITIVE LOGITS
    an
    1.24
    oconut
    1.17
    ავი
    1.13
     ലക്ഷ
    1.12
     bumpy
    1.10
     fois
    1.09
    খা
    1.08
    neath
    1.08
    ்ட
    1.08
     tangy
    1.07
    Activations Density 0.000%

    No Known Activations