© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 3762
    Prev
    Next
    INDEX
    Explanations

    code, data, and concepts

    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_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
    are
    0.40
    è
    0.37
    ل
    0.37
    el
    0.36
    est
    0.36
    ید
    0.35
    ت
    0.35
    ert
    0.35
    ando
    0.34
    ids
    0.34
    POSITIVE LOGITS
     nbsp
    0.45
     откри
    0.37
    _",
    0.35
     ойноо
    0.34
     конца
    0.33
     எனவும்
    0.33
     voila
    0.33
     disponibil
    0.33
     사용
    0.33
     Также
    0.33
    Activations Density 0.190%

    No Known Activations