© 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. 22-GEMMASCOPE-RES-131K
    7. 27320
    Prev
    Next
    INDEX
    Explanations

    code and technical contexts

    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
     that
    -1.32
     when
    -1.22
     before
    -1.18
     other
    -1.14
     all
    -1.10
     with
    -1.10
    тка
    -1.05
    十一
    -1.03
    Ｅ
    -1.02
     each
    -0.99
    POSITIVE LOGITS
     birçok
    1.17
     
    1.13
    じゃなくて
    1.10
     fonctionnent
    1.07
     annoncé
    1.05
     vieler
    1.03
     magnifiques
    1.01
     DOMINGO
    1.01
     auront
    1.00
     insanely
    0.99
    Activations Density 0.019%

    No Known Activations