© 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. 22-GEMMASCOPE-RES-131K
    7. 128216
    Prev
    Next
    INDEX
    Explanations

    NOAA Administration buildings

    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_22/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
    ruguay
    -1.83
    geox
    -1.70
    nikon
    -1.68
    roland
    -1.59
     your
    -1.56
    panasonic
    -1.55
    旆
    -1.52
     dubious
    -1.52
    seiko
    -1.48
     their
    -1.48
    POSITIVE LOGITS
    '
    1.66
    B
    1.65
    l
    1.63
    e
    1.59
    ES
    1.58
    IC
    1.50
    ET
    1.45
    UL
    1.45
    AN
    1.44
    IN
    1.43
    Activations Density 0.002%

    No Known Activations