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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 21401
    Prev
    Next
    INDEX
    Explanations

    file path and name

    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
    -
    0.44
    ικής
    0.33
    र्न
    0.33
    ρίας
    0.33
    WebSocket
    0.33
    替换
    0.32
    Push
    0.30
    $-$
    0.30
     toug
    0.30
     nutshell
    0.30
    POSITIVE LOGITS
    idx
    0.42
    name
    0.37
    .’
    0.35
    list
    0.34
    ':
    0.34
    ';
    0.34
    /'
    0.34
     \\..
    0.34
    url
    0.33
    raw
    0.33
    Activations Density 0.019%

    No Known Activations