© 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. 149339
    Prev
    Next
    INDEX
    Explanations

    formal address; numbers; celestial bodies; media titles

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

    thousand words, millions more, framework experience

    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
    ↵↵
    0.45
     خواست
    0.45
    NIA
    0.44
    ﺋ
    0.44
     Christie
    0.43
    VOA
    0.43
    IA
    0.43
    REAT
    0.42
    PARTMENT
    0.42
    EXPORT
    0.42
    POSITIVE LOGITS
     écrite
    0.54
    roku
    0.51
     करूं
    0.49
     ถาม
    0.49
    תוך
    0.49
     学
    0.48
    बाइक
    0.48
     अस
    0.47
     ऊंची
    0.46
    unken
    0.46
    Activations Density 0.001%

    No Known Activations