© 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. 11436
    Prev
    Next
    INDEX
    Explanations

    questions asking why or how long

    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
    沔
    0.40
     Confirm
    0.39
    correct
    0.38
    Также
    0.38
    correcto
    0.38
     confirm
    0.37
    innaker
    0.36
     Также
    0.36
    연
    0.36
    assurer
    0.36
    POSITIVE LOGITS
     containment
    0.42
    ខ្ល
    0.40
     administra
    0.40
     refinery
    0.39
     divor
    0.38
     saline
    0.38
     geometri
    0.38
     lys
    0.38
    很难
    0.38
     exiled
    0.38
    Activations Density 0.000%

    No Known Activations