© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34872
    Prev
    Next
    INDEX
    Explanations

    you are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     toma
    0.40
     கட்சி
    0.40
    产业
    0.40
    ťou
    0.40
     plufieurs
    0.39
    ="..\
    0.39
     cloudy
    0.39
     ചെയ്ത
    0.39
     ديسمبر
    0.39
     ")");
    0.39
    POSITIVE LOGITS
     cuero
    0.44
    ါ
    0.42
    aol
    0.42
    ?
    0.40
     quarries
    0.40
    agues
    0.40
     Prakt
    0.38
    র্মে
    0.38
    STRUCTIONS
    0.38
     troupes
    0.38
    Activations Density 0.000%

    No Known Activations