© 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. 71588
    Prev
    Next
    INDEX
    Explanations

    flight data

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

    issues, manipulation, and research

    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
     kapcsolat
    0.51
    ｻ
    0.49
     ℃
    0.47
    水の
    0.47
     headwinds
    0.47
     immortality
    0.47
     CAGR
    0.46
     freq
    0.46
    ﾀ
    0.46
     duality
    0.45
    POSITIVE LOGITS
     araştırm
    0.49
     Investigative
    0.48
     जाहीर
    0.47
     Debate
    0.46
    ető
    0.46
    旨在
    0.46
     Journalism
    0.45
     Integrative
    0.44
     investigación
    0.44
    endaftaran
    0.42
    Activations Density 0.001%

    No Known Activations