© 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. 42957
    Prev
    Next
    INDEX
    Explanations

    introductions 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
     konkrete
    -1.40
     decidi
    -1.30
     melhorar
    -1.30
    達が
    -1.28
     tatsächlich
    -1.28
     действительно
    -1.25
     frequentemente
    -1.25
    目前
    -1.24
    eronau
    -1.23
    菝
    -1.23
    POSITIVE LOGITS
     a
    1.60
     at
    1.56
     in
    1.45
     as
    1.42
     by
    1.35
    我先
    1.20
     also
    1.19
    oulos
    1.18
     również
    1.17
    amico
    1.17
    Activations Density 0.029%

    No Known Activations