Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 36933
    Prev
    Next
    INDEX
    Explanations

    similar, MST, pile, born, other

    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
    夫
    0.48
    d
    0.44
    レイ
    0.44
    r
    0.43
    引
    0.43
     riguard
    0.42
    配列
    0.42
    m
    0.42
    n
    0.42
    ዑ
    0.42
    POSITIVE LOGITS
    但是在
    0.52
     ولكن
    0.45
     profesionales
    0.45
    但是
    0.44
     বর্তমানে
    0.43
     ప్రస్తుతం
    0.42
     නමුත්
    0.42
    ترین
    0.41
    ionali
    0.41
     profesional
    0.41
    Activations Density 0.004%

    No Known Activations