© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8945
    Prev
    Next
    INDEX
    Explanations

    multiplier and divisor

    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
     we
    -3.13
     You
    -2.73
    }
    -2.19
     получил
    -2.16
    {
    -2.13
     But
    -2.11
    啬
    -2.09
    REFERRED
    -2.05
    )
    -2.03
     інші
    -1.98
    POSITIVE LOGITS
    Ꮸ
    2.23
    i
    2.19
     نیز
    2.13
    How
    2.05
    縯
    2.02
    d
    1.95
    Why
    1.92
    تها
    1.91
    勠
    1.91
        
    1.89
    Activations Density 0.003%

    No Known Activations