© 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. 7695
    Prev
    Next
    INDEX
    Explanations

    history of

    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
    在住
    -1.63
     eerst
    -1.52
     volledige
    -1.48
     geweldig
    -1.48
     altamente
    -1.46
     originalmente
    -1.45
     helemaal
    -1.44
     wła
    -1.44
     naast
    -1.44
     animados
    -1.42
    POSITIVE LOGITS
     of
    2.83
    f
    2.09
    li
    2.06
    j
    2.03
    m
    2.02
    Since
    1.95
    x
    1.95
    q
    1.91
    However
    1.90
    th
    1.88
    Activations Density 0.014%

    No Known Activations