© 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. 112381
    Prev
    Next
    INDEX
    Explanations

    home and workplace

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

    Oil serves multiple roles

    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
    ᔾ
    0.45
    eterminate
    0.44
    ULTY
    0.42
     unsurpassed
    0.42
     серию
    0.41
    UGHT
    0.41
    σεις
    0.40
    艶
    0.40
    সম্পাদকীয়
    0.40
     uninterrupted
    0.40
    POSITIVE LOGITS
    ।)
    0.49
     طلعت
    0.45
     كويس
    0.44
     حوالہ
    0.43
     स्किप
    0.42
     کھیلنے
    0.42
     فأ
    0.42
    ]<<
    0.41
    Pennsylvania
    0.41
    ότερα
    0.41
    Activations Density 0.001%

    No Known Activations