© 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. 133061
    Prev
    Next
    INDEX
    Explanations

    Metro, represents overall

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

    actual information

    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
     kendi
    0.52
    ↵
    0.51
     nego
    0.48
     mimetype
    0.48
    ختی
    0.46
    یمی
    0.46
     Evam
    0.46
    含义
    0.45
     Kopf
    0.45
     kelu
    0.43
    POSITIVE LOGITS
     illustrative
    0.46
     ईस्ट
    0.44
    ERA
    0.43
     учреждения
    0.43
    辮
    0.43
     neutrons
    0.42
     senators
    0.42
    職業
    0.42
    തിനാൽ
    0.42
     atoms
    0.42
    Activations Density 0.000%

    No Known Activations