© 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. 40-GEMMASCOPE-2-RES-262K
    4. 16218
    Prev
    Next
    INDEX
    Explanations

    code comments and formatting

    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_40_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
    ێنی
    0.39
    ཊ
    0.36
    }^{*}$,
    0.36
    <unused710>
    0.36
    の中で
    0.36
    য্
    0.36
    +"','"+
    0.35
     accompl
    0.35
     ظِلِّ
    0.35
     lengkap
    0.35
    POSITIVE LOGITS
    <b>
    1.34
    <strong>
    1.30
     **
    0.81
     mathbf
    0.68
    //
    0.60
    mathbf
    0.59
    𝗧
    0.55
     '''
    0.54
    #
    0.54
    <h2>
    0.54
    Activations Density 0.078%

    No Known Activations