© 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. 10991
    Prev
    Next
    INDEX
    Explanations

    adding new qualifiers

    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
    ancien
    0.38
     кризи
    0.38
    wię
    0.36
    菒
    0.35
    Resposta
    0.35
    Atual
    0.35
    Languages
    0.34
    Textbox
    0.34
    낡
    0.34
    ímav
    0.34
    POSITIVE LOGITS
     broader
    0.38
     a
    0.36
     the
    0.36
     new
    0.35
     other
    0.35
     camera
    0.34
     extraneous
    0.33
     second
    0.33
     latter
    0.32
     subsequent
    0.32
    Activations Density 0.475%

    No Known Activations