© 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. 40-GEMMASCOPE-2-RES-262K
    7. 7982
    Prev
    Next
    INDEX
    Explanations

    code assignment syntax

    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
    ichés
    0.22
    🖍
    0.22
    <unused362>
    0.21
    💌
    0.21
     سلاٹس
    0.21
    ,—
    0.21
     rameaux
    0.21
    clampsia
    0.21
    ❧
    0.21
     sacerd
    0.21
    POSITIVE LOGITS
    <tr>
    0.27
     abc
    0.27
    0.27
     "[
    0.26
     ABC
    0.26
     <
    0.26
     "
    0.26
     d
    0.25
    abcdef
    0.25
     \
    0.25
    Activations Density 0.129%

    No Known Activations