© 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. 8498
    Prev
    Next
    INDEX
    Explanations

    help people achieve goals

    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
    including
    -1.23
     between
    -1.17
     continuación
    -1.15
     vieles
    -1.15
    iestety
    -1.11
     mediados
    -1.09
     including
    -1.08
     existing
    -1.05
     await
    -1.05
     incluindo
    -1.03
    POSITIVE LOGITS
     eind
    1.20
    .
    1.16
    STORY
    1.13
    <>());
    1.13
    rechten
    1.10
    🥱
    1.10
    */,
    1.08
    стные
    1.07
    pout
    1.06
    殒
    1.05
    Activations Density 0.077%

    No Known Activations