© 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. 42991
    Prev
    Next
    INDEX
    Explanations

    duration from start

    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
     senare
    -1.14
     liknande
    -1.12
    iência
    -1.12
    чним
    -1.11
     indiri
    -1.07
    estens
    -1.06
    dige
    -1.06
    Atoms
    -1.05
     recenti
    -1.05
    доми
    -1.02
    POSITIVE LOGITS
     that
    1.99
     which
    1.85
     until
    1.62
     time
    1.45
     to
    1.44
    Perhaps
    1.43
     Perhaps
    1.36
     any
    1.32
     here
    1.32
     perhaps
    1.30
    Activations Density 0.098%

    No Known Activations