© 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. 34-GEMMASCOPE-RES-131K
    7. 64514
    Prev
    Next
    INDEX
    Explanations

    how questions

    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_34/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
     exista
    -1.36
     interesses
    -1.30
    specified
    -1.24
    oping
    -1.23
    glied
    -1.23
     botines
    -1.22
     gustos
    -1.21
     pantalones
    -1.19
    pantalón
    -1.19
     manualidades
    -1.18
    POSITIVE LOGITS
     does
    3.36
     do
    2.98
     did
    2.75
     can
    2.69
     are
    2.56
     would
    2.16
     should
    2.11
     might
    1.95
     will
    1.95
     has
    1.82
    Activations Density 0.064%

    No Known Activations