© 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. 99764
    Prev
    Next
    INDEX
    Explanations

    Nokia, Portsmouth, cathode

    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
    
    -2.78
    啬
    -2.77
    〠
    -2.70
    晅
    -2.47
    马逊
    -2.42
     archaic
    -2.38
    潾
    -2.38
    𓇼
    -2.36
    瑧
    -2.34
    maglia
    -2.33
    POSITIVE LOGITS
    s
    4.44
    e
    3.91
    .
    3.25
    2
    3.17
    0
    3.13
    9
    3.02
    ll
    2.97
    (
    2.84
     It
    2.80
    3
    2.80
    Activations Density 0.003%

    No Known Activations