© 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. 14823
    Prev
    Next
    INDEX
    Explanations

    code blocks

    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
     derfor
    -1.44
     in
    -1.43
     operar
    -1.41
     setor
    -1.30
    יש
    -1.27
     inglese
    -1.27
    (´
    -1.26
     därför
    -1.24
     only
    -1.23
    ד
    -1.23
    POSITIVE LOGITS
    already
    1.61
     magnificent
    1.59
    probably
    1.48
     marvelous
    1.45
    several
    1.41
    albeit
    1.41
    perhaps
    1.40
    presumably
    1.40
    currently
    1.40
     compromisos
    1.39
    Activations Density 0.017%

    No Known Activations