© 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. 7734
    Prev
    Next
    INDEX
    Explanations

    parking spaces, passes, and lots

    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
     และ
    -2.47
    僂
    -2.36
     teclas
    -2.31
    軚
    -2.28
    摃
    -2.25
    骓
    -2.20
    cised
    -2.16
     所以
    -2.14
     It
    -2.13
    en
    -2.11
    POSITIVE LOGITS
    蚡
    2.78
     семь
    2.52
    虓
    2.48
    -
    2.27
     theses
    2.27
     disagreements
    2.27
     eventual
    2.25
    }$
    2.23
    klaim
    2.20
     erst
    2.19
    Activations Density 0.003%

    No Known Activations