© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83938
    Prev
    Next
    INDEX
    Explanations

    ending or continuing statements

    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
     &=
    -1.36
    Ἡ
    -1.35
    ₤
    -1.30
    ственного
    -1.29
     also
    -1.27
    Ine
    -1.25
     desses
    -1.22
    <th>
    -1.22
     повседнев
    -1.22
    kkue
    -1.21
    POSITIVE LOGITS
     out
    1.56
     dlouho
    1.45
     each
    1.41
     after
    1.35
    nachron
    1.27
     solchen
    1.25
     of
    1.23
     礼物
    1.22
    ⽉
    1.20
    erweise
    1.19
    Activations Density 0.135%

    No Known Activations