© 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. 194066
    Prev
    Next
    INDEX
    Explanations

    teaching and informational content

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

    questions about removing files

    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
    6
    0.53
    8
    0.53
    L
    0.50
    9
    0.48
    AL
    0.48
    7
    0.48
    RE
    0.47
    B
    0.46
    MON
    0.46
    4
    0.46
    POSITIVE LOGITS
    ቱም
    0.52
    𝘯
    0.50
     Плавание
    0.48
     intracranial
    0.47
     Stimme
    0.45
    드의
    0.45
     dimer
    0.44
    স্বর
    0.43
    坞
    0.43
    枞
    0.43
    Activations Density 0.000%

    No Known Activations