© 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. 7401
    Prev
    Next
    INDEX
    Explanations

    clarity and simplicity

    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
    重新
    1.04
    Д
    0.94
     ойношот
    0.94
     Geoff
    0.92
     Chemin
    0.92
    PropertyName
    0.90
    MIUM
    0.89
    o
    0.88
    вто
    0.88
    vati
    0.85
    POSITIVE LOGITS
    ή
    0.89
     blatant
    0.83
    תי
    0.83
     ľudí
    0.82
    社員
    0.82
     तय
    0.82
     प्रत
    0.81
     ljudi
    0.80
     svým
    0.79
     sü
    0.78
    Activations Density 0.002%

    No Known Activations