© 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. 113387
    Prev
    Next
    INDEX
    Explanations

    vehicle incidents near streets

    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
    still
    -1.53
    somewhat
    -1.41
    けっこう
    -1.31
    sometimes
    -1.26
    everybody
    -1.21
    slightly
    -1.19
    featuring
    -1.17
    slowly
    -1.16
    だいぶ
    -1.16
    might
    -1.16
    POSITIVE LOGITS
     or
    1.66
     during
    1.35
     after
    1.34
    bø
    1.34
     and
    1.34
     또는
    1.33
    +='
    1.30
     before
    1.28
     showed
    1.27
    又は
    1.27
    Activations Density 0.108%

    No Known Activations