© 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. 59678
    Prev
    Next
    INDEX
    Explanations

    code or system components

    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
     one
    -1.48
    ֮
    -1.48
     Seizures
    -1.38
     hindering
    -1.37
     fortsetter
    -1.36
     empathetic
    -1.36
     touted
    -1.34
     longstanding
    -1.32
     supposedly
    -1.30
    taxia
    -1.28
    POSITIVE LOGITS
     you
    1.48
    leness
    1.41
    部分を
    1.41
     burada
    1.39
     and
    1.36
    "<
    1.34
     durante
    1.32
    nne
    1.30
     ejes
    1.29
     掃除
    1.29
    Activations Density 0.010%

    No Known Activations