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. 16-GEMMASCOPE-2-RES-262K
    4. 141937
    Prev
    Next
    INDEX
    Explanations

    utility functions or classes

    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
    bumptech
    0.47
    ল
    0.44
    ها
    0.43
    んにちは
    0.43
    න්ධ
    0.43
    метри
    0.42
     eines
    0.41
    ।"
    0.41
    හෝ
    0.41
    リティ
    0.41
    POSITIVE LOGITS
    the
    0.46
     haunts
    0.43
     N
    0.37
     তাড়
    0.36
     For
    0.35
     The
    0.35
     In
    0.35
    אס
    0.34
     первую
    0.34
     Arts
    0.33
    Activations Density 0.002%

    No Known Activations