© 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. 125577
    Prev
    Next
    INDEX
    Explanations

    garden views or sea views

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

    OMG, exclamations, and enthusiastic greetings

    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
     kuid
    0.42
     possède
    0.39
     diferença
    0.38
     .
    0.38
     Detailed
    0.38
     Differences
    0.37
     Bournemouth
    0.37
     tačiau
    0.37
    ട്ടുണ്ട്
    0.37
     Dorchester
    0.37
    POSITIVE LOGITS
    ส
    0.52
    로
    0.51
     რე
    0.50
    އ
    0.50
    วา
    0.50
    大丈夫
    0.50
    在她
    0.48
    ലോ
    0.47
    áte
    0.46
    ה
    0.46
    Activations Density 0.000%

    No Known Activations