© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 38216
    Prev
    Next
    INDEX
    Explanations

    bullet points or bolded lists

    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
    ņas
    0.58
    قیع
    0.54
    ២
    0.52
    ٢
    0.52
    ])$.
    0.50
    วิว
    0.47
    ទេ។
    0.46
    лев
    0.46
     squadrons
    0.45
     हाइ
    0.45
    POSITIVE LOGITS
    【
    0.45
     Evet
    0.44
     a
    0.41
    ừ
    0.41
     @
    0.41
    人物
    0.41
    摯
    0.41
    数
    0.40
     Atlanta
    0.40
     Funded
    0.40
    Activations Density 0.000%

    No Known Activations