© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45054
    Prev
    Next
    INDEX
    Explanations

    governed by

    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
     and
    -1.59
     svým
    -1.45
     itself
    -1.45
     člá
    -1.41
    蒟
    -1.38
    時間に
    -1.34
     still
    -1.34
     část
    -1.34
     måde
    -1.32
    formatics
    -1.30
    POSITIVE LOGITS
     “
    1.24
     является
    1.21
    <td>
    1.21
    彼は
    1.17
     tikai
    1.16
    .)
    1.15
    livro
    1.14
    ̳
    1.14
    >
    1.14
    .”
    1.13
    Activations Density 0.165%

    No Known Activations