© 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. 127768
    Prev
    Next
    INDEX
    Explanations

    best practices for installing

    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
     своих
    -1.88
     همان
    -1.80
    ;:
    -1.78
     своего
    -1.67
    秾
    -1.66
     événement
    -1.65
     its
    -1.63
    -:
    -1.59
     a
    -1.52
    、「
    -1.52
    POSITIVE LOGITS
     for
    2.02
     from
    2.02
     these
    1.96
     of
    1.95
     this
    1.75
     including
    1.74
     Some
    1.62
     additional
    1.55
    了一些
    1.54
     not
    1.52
    Activations Density 0.319%

    No Known Activations