© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74783
    Prev
    Next
    INDEX
    Explanations

    specifying quantity or selection

    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
     and
    -2.86
     but
    -1.65
     first
    -1.43
    鴣
    -1.40
    ріш
    -1.39
    fă
    -1.31
    dă
    -1.27
    Гаран
    -1.27
    ardige
    -1.23
     Tüm
    -1.23
    POSITIVE LOGITS
     others
    1.49
     they
    1.48
    various
    1.37
     other
    1.36
    </b>
    1.32
     mentales
    1.30
    ЛИ
    1.28
     famoso
    1.27
    actéristi
    1.26
    frases
    1.23
    Activations Density 0.061%

    No Known Activations