© 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. 67415
    Prev
    Next
    INDEX
    Explanations

    movement forward and back

    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
     which
    -1.38
     now
    -1.23
     heute
    -1.20
    now
    -1.20
    ]+
    -1.13
     voor
    -1.08
    鵲
    -1.07
    cía
    -1.06
    xml
    -1.05
    ｂ
    -1.04
    POSITIVE LOGITS
    osing
    1.28
     .......
    1.27
     แต่
    1.26
     condenado
    1.22
     peligroso
    1.21
    leggio
    1.21
     meestal
    1.20
     towards
    1.16
    sighs
    1.16
     suele
    1.13
    Activations Density 0.012%

    No Known Activations