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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 14059
    Prev
    Next
    INDEX
    Explanations

    Holy Roman Empire

    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
     :\
    0.66
     +\
    0.65
    (\
    0.64
     -\
    0.63
    ({\
    0.62
    weiß
    0.61
     כ
    0.59
    ENTE
    0.59
     Cellulose
    0.57
    ᱘
    0.57
    POSITIVE LOGITS
    es
    0.68
    ur
    0.59
     studente
    0.59
    b
    0.58
     academ
    0.54
     студент
    0.54
    as
    0.53
    ੴ
    0.52
    م
    0.51
    eln
    0.50
    Activations Density 0.001%

    No Known Activations