© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69916
    Prev
    Next
    INDEX
    Explanations

    into the

    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
    </b>
    -1.16
     of
    -1.15
     では
    -1.14
     than
    -1.12
     then
    -1.09
    рию
    -1.09
    m
    -1.08
    both
    -1.07
     إذا
    -1.05
     have
    -1.04
    POSITIVE LOGITS
     enormes
    1.27
     中式
    1.17
     químicos
    1.14
     kolye
    1.13
    textarea
    1.13
     menek
    1.13
    と感じ
    1.11
     crescita
    1.10
     byli
    1.09
     koment
    1.09
    Activations Density 0.104%

    No Known Activations