© 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. 110620
    Prev
    Next
    INDEX
    Explanations

    changed anatomy, imaging, room

    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
    s
    0.55
    and
    0.53
    The
    0.48
    :
    0.48
     (
    0.46
    in
    0.45
    nuts
    0.44
    ellum
    0.44
    j
    0.44
    type
    0.42
    POSITIVE LOGITS
     የማይ
    0.55
    郘
    0.50
    শ্বর
    0.49
    㦣
    0.49
    鸴
    0.49
    श्यक
    0.48
    ేశ
    0.48
    <<"\
    0.47
     Благодаря
    0.47
     professionnel
    0.46
    Activations Density 0.004%

    No Known Activations