© 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. 12862
    Prev
    Next
    INDEX
    Explanations

    allowing things to happen

    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
    謊
    -1.42
     hyvä
    -1.41
     régal
    -1.40
     provoquer
    -1.37
     almak
    -1.35
    などなど
    -1.34
     équilibre
    -1.34
    unile
    -1.33
     besseren
    -1.33
    🥏
    -1.32
    POSITIVE LOGITS
     was
    1.80
     тот
    1.69
     who
    1.68
     kvinnor
    1.64
     in
    1.55
     that
    1.48
    ursday
    1.47
    "",
    1.42
    は約
    1.41
     unable
    1.39
    Activations Density 0.025%

    No Known Activations