© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200445
    Prev
    Next
    INDEX
    Explanations

    mode decomposition verify check vary deleted

    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
    ת
    0.52
    s
    0.50
    א
    0.50
    同士
    0.49
    ing
    0.46
     наси
    0.46
    (
    0.46
    \
    0.45
     things
    0.44
    age
    0.44
    POSITIVE LOGITS
     закона
    0.55
    వంటి
    0.50
     sifatida
    0.49
     医学
    0.48
    jegyz
    0.48
    čen
    0.47
    adə
    0.47
     veditabbo
    0.47
     کرا
    0.47
     તરીકે
    0.46
    Activations Density 0.001%

    No Known Activations