© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113965
    Prev
    Next
    INDEX
    Explanations

    community and world

    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
     with
    -1.92
     for
    -1.63
     while
    -1.49
     from
    -1.47
     on
    -1.47
     because
    -1.40
     all
    -1.36
     their
    -1.34
     you
    -1.32
     including
    -1.31
    POSITIVE LOGITS
     ARISING
    1.38
    gives
    1.30
    though
    1.27
    choose
    1.24
    ."
    1.22
    but
    1.21
    把她
    1.20
    ⅝
    1.20
    У
    1.20
    スポン
    1.19
    Activations Density 0.079%

    No Known Activations