© 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. 15892
    Prev
    Next
    INDEX
    Explanations

    game or team results

    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
     his
    -1.44
     but
    -1.29
     himself
    -1.24
     now
    -1.21
    :
    -1.13
     already
    -1.08
     time
    -1.05
    ####
    -1.04
     described
    -1.04
    WillAppear
    -1.03
    POSITIVE LOGITS
    paravant
    1.27
     they
    1.19
     ARISING
    1.16
     rassemb
    1.16
     fournisseurs
    1.16
    TryDecode
    1.13
    zonych
    1.12
    Външни
    1.11
     wspól
    1.10
    他们在
    1.10
    Activations Density 0.016%

    No Known Activations