© 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. 7626
    Prev
    Next
    INDEX
    Explanations

    commas and semicolons, often followed by 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
     bonitos
    -2.72
     divertidos
    -2.63
    觏
    -2.61
     sincero
    -2.59
     embarazada
    -2.55
     ubiquitous
    -2.50
    ⸫
    -2.44
     cansado
    -2.42
     muñecas
    -2.38
    蹰
    -2.38
    POSITIVE LOGITS
    p
    3.28
    n
    3.25
    m
    2.84
    as
    2.81
    z
    2.67
    to
    2.63
    袮
    2.63
    2
    2.58
    ],
    2.52
    7
    2.52
    Activations Density 0.005%

    No Known Activations