© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 204531
    Prev
    Next
    INDEX
    Explanations

    arguments or descriptions

    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
    ̹
    0.41
    detailed
    0.40
    check
    0.40
    decoration
    0.39
    olith
    0.39
    halla
    0.38
    shand
    0.38
    nal
    0.38
    blems
    0.38
    dividend
    0.38
    POSITIVE LOGITS
     EXAMPLE
    0.42
     Include
    0.39
     INCLUDE
    0.38
    撂
    0.38
     tiba
    0.38
    সঙ্গে
    0.38
     equipped
    0.38
    뽐
    0.38
    ี่ยว
    0.37
    玹
    0.37
    Activations Density 0.002%

    No Known Activations