© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12267
    Prev
    Next
    INDEX
    Explanations

    line, type, group, or patient

    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
    telser
    -1.19
    他們
    -1.18
     cellule
    -1.17
     capot
    -1.17
     histó
    -1.16
    他们
    -1.16
     Système
    -1.16
     OPERATION
    -1.15
     内衣
    -1.14
    ñales
    -1.13
    POSITIVE LOGITS
     For
    1.19
    n
    1.08
    with
    1.08
    \\
    1.07
    c
    1.06
     哪些
    1.04
     Information
    1.02
    Y
    1.02
    f
    1.02
     Are
    1.02
    Activations Density 0.073%

    No Known Activations