© 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. 4494
    Prev
    Next
    INDEX
    Explanations

    need to / able to

    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
    that
    0.75
    ’
    0.64
    ،
    0.63
    ками
    0.58
    '
    0.57
    5
    0.57
    4
    0.57
    this
    0.56
    ке
    0.55
    ках
    0.54
    POSITIVE LOGITS
     to
    0.76
     kurze
    0.68
     neue
    0.68
    é
    0.68
     între
    0.67
    ي
    0.66
    ূর্ব
    0.65
    m
    0.61
     požad
    0.61
    松
    0.61
    Activations Density 0.517%

    No Known Activations