© 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. 33617
    Prev
    Next
    INDEX
    Explanations

    object attributes and identifiers

    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
    several
    -1.38
    Kommentare
    -1.36
    Preparazione
    -1.34
     作り方
    -1.28
    frequently
    -1.28
     pakan
    -1.27
    もあって
    -1.24
    もありますが
    -1.24
     naudo
    -1.14
     всеми
    -1.13
    POSITIVE LOGITS
     and
    1.24
    OCCURRED
    1.13
    úcia
    1.13
    _
    1.03
    ७
    0.98
     dergleichen
    0.98
    mathrm
    0.95
     klachten
    0.95
    ३
    0.95
    ()])
    0.94
    Activations Density 0.003%

    No Known Activations