© 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. 67556
    Prev
    Next
    INDEX
    Explanations

    virtues and psychological states

    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
     to
    -1.66
     of
    -1.57
     bensin
    -1.34
     and
    -1.33
     pantal
    -1.31
     tradis
    -1.30
     hawa
    -1.27
     花园
    -1.25
     eeu
    -1.23
     vélos
    -1.21
    POSITIVE LOGITS
     Menschheit
    1.35
     protože
    1.30
     größeren
    1.28
     exponer
    1.27
     großen
    1.27
    диться
    1.21
    ︴
    1.21
     anybody
    1.21
     sólo
    1.18
    んでいます
    1.18
    Activations Density 0.146%

    No Known Activations