© 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. 198049
    Prev
    Next
    INDEX
    Explanations

    requiring information or action

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

    requirements

    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
     powied
    1.17
    는
    1.14
     pregunt
    1.07
     comenzar
    1.07
    是
    1.05
    كور
    1.04
     estadísticas
    1.02
    ג
    1.02
     communauté
    1.00
     gobernador
    1.00
    POSITIVE LOGITS
    il
    1.64
    b
    1.64
    x
    1.64
    as
    1.62
    et
    1.51
    ut
    1.51
    on
    1.49
    c
    1.48
    p
    1.46
    ab
    1.41
    Activations Density 0.065%

    No Known Activations