© 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. 25295
    Prev
    Next
    INDEX
    Explanations

    velocity and distance

    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
     idee
    -1.24
     wagen
    -1.20
     effec
    -1.18
    Ça
    -1.15
     exigences
    -1.13
     gitar
    -1.11
     гита
    -1.11
     eier
    -1.10
     véritables
    -1.09
     ferie
    -1.09
    POSITIVE LOGITS
     after
    1.63
     pelatihan
    1.54
     from
    1.51
     at
    1.42
     time
    1.40
     until
    1.34
     since
    1.33
     alér
    1.32
     dél
    1.30
    шной
    1.28
    Activations Density 0.017%

    No Known Activations