© 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. 67935
    Prev
    Next
    INDEX
    Explanations

    fiction characters and names

    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
    colgante
    -1.53
    blå
    -1.48
     desmotiv
    -1.34
    少々
    -1.34
    Joueur
    -1.33
     harrowing
    -1.32
     špec
    -1.31
    those
    -1.30
    Halaman
    -1.30
     aqueles
    -1.29
    POSITIVE LOGITS
     could
    1.44
     there
    1.33
    да
    1.30
    잉
    1.28
    If
    1.28
     if
    1.27
    .
    1.25
     getting
    1.24
     as
    1.22
    पुर
    1.20
    Activations Density 0.030%

    No Known Activations