© 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. 10-GEMMASCOPE-RES-131K
    7. 85568
    Prev
    Next
    INDEX
    Explanations

    ln(x)

    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
    鋮
    -3.00
    
    -2.98
    \"");
    -2.81
    ꦒ
    -2.80
    𓄹
    -2.75
    ⽌
    -2.67
    ጺ
    -2.66
    ે
    -2.66
    ﺰ
    -2.64
    龊
    -2.48
    POSITIVE LOGITS
    \
    3.42
    *
    3.39
    en
    3.25
    n
    3.06
    '
    2.98
    ed
    2.86
    r
    2.81
    "—
    2.81
     '
    2.78
    x
    2.75
    Activations Density 0.002%

    No Known Activations