© 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. 109411
    Prev
    Next
    INDEX
    Explanations

    deployment context

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

    how to configure

    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
    слав
    0.51
     まま
    0.49
     револю
    0.47
    новен
    0.45
    ден
    0.44
    ОР
    0.44
    нется
    0.44
    ᱯ
    0.44
    ウンド
    0.44
    де
    0.44
    POSITIVE LOGITS
     hvordan
    0.53
     omdat
    0.52
     how
    0.52
     bagaimana
    0.48
     Mitarbeiter
    0.46
     conversa
    0.46
     وضاحت
    0.46
     എങ്ങനെ
    0.46
     cómo
    0.45
     kuidas
    0.45
    Activations Density 0.000%

    No Known Activations