© 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. 100905
    Prev
    Next
    INDEX
    Explanations

    procedures and making changes

    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
    ￠
    0.50
    삑
    0.49
     urząd
    0.48
     BYU
    0.47
    ινε
    0.46
     Correctional
    0.46
     intravenously
    0.46
    quela
    0.45
    ুইস
    0.45
    इए
    0.45
    POSITIVE LOGITS
    I
    0.46
    Schema
    0.44
    ${
    0.43
    IllegalArgument
    0.42
    ipynb
    0.41
    form
    0.40
     I
    0.40
    </code>
    0.40
    ef
    0.39
    ows
    0.39
    Activations Density 0.009%

    No Known Activations