© 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. 16-GEMMASCOPE-2-RES-262K
    7. 8959
    Prev
    Next
    INDEX
    Explanations

    the "superlative" or "defining noun"

    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_16_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
    A
    0.70
    a
    0.69
     A
    0.64
    H
    0.63
    T
    0.62
    W
    0.57
    o
    0.56
     zacz
    0.56
     wszel
    0.55
    ஹ
    0.55
    POSITIVE LOGITS
    ンの
    0.71
    ുമ്പോൾ
    0.70
    linha
    0.59
    produto
    0.59
    porque
    0.57
     که
    0.57
     जिससे
    0.56
    text
    0.55
     کل
    0.55
    ciò
    0.55
    Activations Density 0.368%

    No Known Activations