© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10600
    Prev
    Next
    INDEX
    Explanations

    headings and printing

    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_16k_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
     text
    0.38
    湃
    0.38
     afbeelding
    0.37
     tabular
    0.37
     sepatu
    0.36
    呎
    0.36
    墘
    0.36
    ʌ
    0.36
    apatos
    0.36
     szö
    0.36
    POSITIVE LOGITS
    Heading
    0.61
     heading
    0.58
    headers
    0.54
     bold
    0.53
    bold
    0.52
     Headers
    0.52
    heading
    0.50
     Heading
    0.49
    <b>
    0.48
     fontWeight
    0.48
    Activations Density 0.141%

    No Known Activations