© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126643
    Prev
    Next
    INDEX
    Explanations

    dominates requirement

    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
    ujú
    0.50
    ントン
    0.46
     freshly
    0.45
    雞
    0.44
     confectionery
    0.43
     sağlan
    0.43
     ổ
    0.42
     OE
    0.41
    供應
    0.41
     azúcar
    0.41
    POSITIVE LOGITS
     evocative
    0.45
    methods
    0.42
     Tessa
    0.42
    Life
    0.41
     loob
    0.41
     methods
    0.40
    Cover
    0.40
    Doing
    0.40
    Time
    0.40
    vedo
    0.39
    Activations Density 0.004%

    No Known Activations