© 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. 32135
    Prev
    Next
    INDEX
    Explanations

    runApp

    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
     Vimeo
    0.47
     Video
    0.41
     Warming
    0.40
     Ac
    0.39
    mse
    0.39
    oomla
    0.39
     Vide
    0.38
    <ul>
    0.38
     வீடியோ
    0.38
     Clipping
    0.38
    POSITIVE LOGITS
    웡
    0.41
    repet
    0.40
    бою
    0.40
     বিভ
    0.39
     repet
    0.39
    പേ
    0.38
     frantic
    0.38
     لگاتا
    0.38
     toiletries
    0.37
    হইবে
    0.37
    Activations Density 0.000%

    No Known Activations