© 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. 22-GEMMASCOPE-RES-131K
    7. 33716
    Prev
    Next
    INDEX
    Explanations

    look up specific information

    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_22/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
    dekat
    -1.28
    länge
    -1.28
    siyah
    -1.24
    hasilkan
    -1.24
     their
    -1.23
     Drž
    -1.20
     its
    -1.16
     before
    -1.16
     його
    -1.14
     begin
    -1.11
    POSITIVE LOGITS
    am
    1.42
    u
    1.41
    is
    1.35
    ino
    1.32
    if
    1.30
    or
    1.30
    k
    1.26
    in
    1.24
    es
    1.20
    g
    1.20
    Activations Density 0.000%

    No Known Activations