© 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. 26467
    Prev
    Next
    INDEX
    Explanations

    A followed by colon or number

    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
     in
    -1.59
    moiselle
    -1.44
     on
    -1.32
     begy
    -1.30
    всем
    -1.28
    😮
    -1.27
    əri
    -1.17
    angnya
    -1.16
     when
    -1.13
    уме
    -1.13
    POSITIVE LOGITS
     hinzugefügt
    1.22
    色んな
    1.20
     größe
    1.16
    ⽼
    1.16
     ermöglicht
    1.16
    来週
    1.14
    provides
    1.14
     erhi
    1.13
    ほんとに
    1.09
    diferentes
    1.09
    Activations Density 0.024%

    No Known Activations