© 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. 73709
    Prev
    Next
    INDEX
    Explanations

    obscuring, replenishment, exhaustion, NullException, equilibration, Bournemouth, Bountiful

    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
    ”),
    -3.23
     剤
    -2.84
    ”:
    -2.83
    т
    -2.78
    ”،
    -2.73
    )”
    -2.73
     There
    -2.66
    ”)
    -2.66
     tetapi
    -2.58
    ꦒ
    -2.56
    POSITIVE LOGITS
     "
    3.16
     exceedingly
    2.67
    "
    2.66
     '
    2.48
    <
    2.47
    ...
    2.45
    真的很
    2.45
    ."
    2.45
     vielen
    2.44
     différents
    2.44
    Activations Density 0.008%

    No Known Activations