© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58808
    Prev
    Next
    INDEX
    Explanations

    zodiac signs and angina

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    -3.02
    .’
    -2.44
    扺
    -2.39
    ↵↵
    -2.33
     }
    -2.31
     But
    -2.25
    [
    -2.23
    tedrale
    -2.22
    祤
    -2.22
    但他
    -2.19
    POSITIVE LOGITS
    </i>
    2.39
    𐍆
    2.30
    ╽
    2.20
    釓
    2.17
    e
    2.17
    谈判
    2.14
    坼
    2.13
    ￪
    2.11
    ﾔ
    2.11
     literat
    2.11
    Activations Density 0.002%

    No Known Activations