© 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. 22385
    Prev
    Next
    INDEX
    Explanations

    organization and materiality

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

    common phrases and transitions

    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
     BECAUSE
    0.37
     সম্বন্ধে
    0.35
     অমন
    0.34
     канторы
    0.34
    鳇
    0.33
     있는데
    0.32
     некоторых
    0.32
     Сасик
    0.32
     hãy
    0.32
     checkIf
    0.32
    POSITIVE LOGITS
    1
    0.35
    0.31
     ultimately
    0.31
     explos
    0.31
     scalable
    0.31
    2
    0.30
    ↵
    0.29
     throughout
    0.29
    <0xE2>
    0.29
     unparalleled
    0.28
    Activations Density 0.268%

    No Known Activations