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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54261
    Prev
    Next
    INDEX
    Explanations

    code preprocessor directives

    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
    ꪹ
    -1.74
    ꪻ
    -1.64
    素晴
    -1.55
    极其
    -1.55
    haviours
    -1.49
    AxisSize
    -1.48
    Indien
    -1.48
    PENUTUP
    -1.48
     Inſ
    -1.47
    躓
    -1.47
    POSITIVE LOGITS
    )
    1.82
    u
    1.81
    B
    1.73
    T
    1.58
    s
    1.53
    _
    1.52
    It
    1.46
     '
    1.45
    //
    1.44
    L
    1.44
    Activations Density 0.002%

    No Known Activations