© 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. 84150
    Prev
    Next
    INDEX
    Explanations

    punctuation and punctual words

    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
    ቭ
    -2.48
     This
    -2.33
     iscri
    -2.25
    ondheim
    -2.22
    fficking
    -2.20
    derdag
    -2.16
     она
    -2.09
    Ᏺ
    -2.08
    ữu
    -2.05
    nischer
    -2.05
    POSITIVE LOGITS
    '
    3.08
     \
    2.55
    end
    2.09
    “
    2.02
    n
    2.00
    1
    2.00
    甚至是
    1.97
    \_
    1.93
    我先
    1.93
    ated
    1.92
    Activations Density 0.003%

    No Known Activations