© 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. 128225
    Prev
    Next
    INDEX
    Explanations

    override method

    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
    ꔹ
    -1.64
    imantan
    -1.59
     you
    -1.43
     também
    -1.41
    also
    -1.39
     genitals
    -1.37
    灬
    -1.37
     also
    -1.35
    and
    -1.34
    geſ
    -1.34
    POSITIVE LOGITS
    .
    1.48
    .《
    1.46
    opportunity
    1.41
     éx
    1.41
    tourism
    1.41
    aneity
    1.39
    warranty
    1.39
     formen
    1.38
     débris
    1.38
     linke
    1.38
    Activations Density 0.001%

    No Known Activations