© 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. 40-GEMMASCOPE-2-RES-262K
    7. 204424
    Prev
    Next
    INDEX
    Explanations

    data as function argument or in array/object literal

    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_40_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
     toString
    0.40
    奭
    0.39
    ?...
    0.37
    ওয়া
    0.37
    <0xB0>
    0.36
     dispers
    0.36
    шин
    0.36
    ترك
    0.35
    申し上げ
    0.35
     disperse
    0.35
    POSITIVE LOGITS
     其
    0.41
     Такая
    0.40
    ENTS
    0.39
     ஒருவர்
    0.39
    윗
    0.37
    guien
    0.37
     sir
    0.36
    心配
    0.36
     چنین
    0.36
     compet
    0.36
    Activations Density 0.008%

    No Known Activations