© 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. 201091
    Prev
    Next
    INDEX
    Explanations

    break down

    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
    튀
    0.49
    ци
    0.48
    ку
    0.48
    αν
    0.47
    गतान
    0.47
    ッシュ
    0.46
    면
    0.46
    сан
    0.46
    ട്ടു
    0.45
    ultat
    0.45
    POSITIVE LOGITS
     oms
    0.47
    ermos
    0.40
     brace
    0.39
     obscure
    0.39
     æ
    0.39
     Recol
    0.38
     brems
    0.38
     inci
    0.38
     Constructor
    0.37
    橑
    0.37
    Activations Density 0.002%

    No Known Activations