© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 8225
    Prev
    Next
    INDEX
    Explanations

    introduction, conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     used
    1.02
    /
    1.00
     pakai
    0.99
     yells
    0.98
     files
    0.95
     zum
    0.93
     requests
    0.92
     file
    0.90
    -
    0.90
     orders
    0.90
    POSITIVE LOGITS
    Furthermore
    1.20
    Despite
    1.16
    Benefits
    1.09
    Although
    1.05
    Indeed
    1.04
     Undoubtedly
    1.04
     insanların
    1.03
    Ironically
    1.02
    Perhaps
    1.01
    Acknowled
    1.00
    Activations Density 0.022%

    No Known Activations