© 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. 14879
    Prev
    Next
    INDEX
    Explanations

    numbered list item 2

    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
     Bot
    0.73
     /
    0.70
     SES
    0.70
     및
    0.67
     **
    0.67
     wahrscheinlich
    0.66
     Google
    0.65
     Pinterest
    0.65
     Autob
    0.65
     Etsy
    0.65
    POSITIVE LOGITS
    ệc
    0.84
    \%).
    0.73
    }\}$.
    0.71
    eru
    0.71
    द्वारा
    0.71
     nėra
    0.70
    <unused11>
    0.70
    二是
    0.70
    ಪ್ಪ
    0.69
    )}.
    0.68
    Activations Density 0.072%

    No Known Activations