© 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. 39570
    Prev
    Next
    INDEX
    Explanations

    learning to do

    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
     or
    -1.63
    Any
    -1.52
     this
    -1.39
     any
    -1.38
    Often
    -1.26
     to
    -1.12
     всегда
    -1.09
    #
    -1.09
    Those
    -1.09
    任何
    -1.08
    POSITIVE LOGITS
    puh
    1.36
     perbedaan
    1.26
    拵
    1.20
     pulseira
    1.18
    noin
    1.12
    Voi
    1.10
     who
    1.09
    mvh
    1.09
     anvä
    1.09
     pourquoi
    1.07
    Activations Density 0.065%

    No Known Activations