© 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. 84315
    Prev
    Next
    INDEX
    Explanations

    code that returns a result

    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
    皤
    -1.84
    跸
    -1.63
    koszulka
    -1.61
    垕
    -1.59
    sukienka
    -1.56
    鼍
    -1.48
     mijn
    -1.45
     I
    -1.44
    苤
    -1.41
     мои
    -1.38
    POSITIVE LOGITS
     that
    2.41
    when
    1.99
    When
    1.76
    With
    1.55
    However
    1.52
    Many
    1.52
    with
    1.48
    For
    1.46
    One
    1.43
     esterni
    1.42
    Activations Density 0.005%

    No Known Activations