© 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. 71518
    Prev
    Next
    INDEX
    Explanations

    to which I

    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
    縠
    -1.73
    }$,
    -1.42
     indiví
    -1.41
    がこの
    -1.39
    смот
    -1.38
     ähnlichen
    -1.38
    rainian
    -1.38
    それに
    -1.37
     felpa
    -1.36
    capulco
    -1.34
    POSITIVE LOGITS
     completas
    1.66
    ing
    1.53
    ↵
    1.52
     your
    1.49
     sahen
    1.45
     an
    1.43
     abiertas
    1.41
     gdy
    1.38
     a
    1.38
     avevano
    1.36
    Activations Density 0.040%

    No Known Activations