© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19113
    Prev
    Next
    INDEX
    Explanations

    Salesforce, African, common, explosive, showcast

    np_acts-logits-general · gemini-2.5-flash-lite

    AI product development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    頊
    0.46
     टीचर
    0.45
    궈
    0.44
    riter
    0.44
    Statements
    0.43
    Henry
    0.42
    퍼
    0.42
    piper
    0.41
     dismiss
    0.41
    inches
    0.41
    POSITIVE LOGITS
    和服务
    0.39
     navegador
    0.38
     प्लेयर्स
    0.38
     Nuestros
    0.38
     Gutenberg
    0.38
     Malware
    0.37
     e
    0.37
     STEAM
    0.37
    த்திரை
    0.37
     Kün
    0.37
    Activations Density 0.000%

    No Known Activations