© 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. 202260
    Prev
    Next
    INDEX
    Explanations

    vary, slightly

    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
    תו
    0.48
    usam
    0.46
    酤
    0.46
    તુ
    0.44
     сил
    0.43
    ágoras
    0.42
    тон
    0.42
    acoes
    0.42
    зора
    0.41
    Đ
    0.41
    POSITIVE LOGITS
     April
    0.55
     Australians
    0.52
     atherosclerosis
    0.48
     апреле
    0.46
     autumn
    0.46
     Seasonal
    0.46
    ierra
    0.45
     cervical
    0.45
     atrophy
    0.45
     april
    0.44
    Activations Density 0.001%

    No Known Activations