© 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. 13248
    Prev
    Next
    INDEX
    Explanations

    examples, general information, or generic results

    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
    Ion
    0.49
    ko
    0.48
    ack
    0.46
    X
    0.46
    ion
    0.45
    Ot
    0.45
    Io
    0.45
    Exe
    0.45
    ieel
    0.44
     बा
    0.44
    POSITIVE LOGITS
     toppings
    0.45
    য়ন
    0.44
    丵
    0.44
    하는
    0.43
     varic
    0.43
     fatalities
    0.43
    叙
    0.42
     nomes
    0.41
     dormancy
    0.41
    كلات
    0.41
    Activations Density 0.004%

    No Known Activations