© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11337
    Prev
    Next
    INDEX
    Explanations

    Leapster Variance found on X

    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
    kül
    -0.81
     kiezen
    -0.80
     lograr
    -0.79
    rpg
    -0.79
     utilizing
    -0.77
    nă
    -0.77
     allows
    -0.76
     小学生
    -0.76
     with
    -0.75
    erano
    -0.75
    POSITIVE LOGITS
     apparaître
    0.96
         
    0.81
     voyant
    0.80
    or
    0.79
    Samedi
    0.78
    ոս
    0.76
    especially
    0.74
    🫖
    0.73
     conseiller
    0.73
    EVEN
    0.73
    Activations Density 0.139%

    No Known Activations