© 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. 116097
    Prev
    Next
    INDEX
    Explanations

    helping you or things

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

    sections, customs, find

    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
     conformidad
    0.46
     ನಾನು
    0.46
    पहर
    0.45
    жено
    0.44
    گاہ
    0.44
    娑
    0.43
     জানাতে
    0.43
     Bismillahirrah
    0.43
     zdjęcie
    0.43
    словно
    0.43
    POSITIVE LOGITS
    ll
    0.51
     an
    0.50
     lower
    0.47
     countries
    0.46
    lower
    0.46
     a
    0.44
    ama
    0.44
     from
    0.43
    '.
    0.42
    1
    0.42
    Activations Density 0.002%

    No Known Activations