© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22400
    Prev
    Next
    INDEX
    Explanations

    and more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     And
    0.58
     or
    0.57
     I
    0.55
     и
    0.52
    性和
    0.51
     و
    0.50
     மட்டும்
    0.50
     आणि
    0.49
     বা
    0.49
     and
    0.47
    POSITIVE LOGITS
    வற்ற
    0.57
    تي
    0.57
    માં
    0.54
    dır
    0.53
    скільки
    0.52
    !
    0.52
    czną
    0.51
    лла
    0.51
    သော
    0.50
    ών
    0.50
    Activations Density 0.033%

    No Known Activations