© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 7887
    Prev
    Next
    INDEX
    Explanations

    home, tweet, grammar commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     and
    0.65
     S
    0.61
     K
    0.51
     nutrients
    0.50
     semua
    0.49
    愠
    0.49
    and
    0.49
     people
    0.49
     rodents
    0.49
     B
    0.49
    POSITIVE LOGITS
     a
    0.66
     the
    0.64
    ।
    0.64
    1
    0.64
    6
    0.60
    0
    0.59
    。
    0.59
    3
    0.58
    4
    0.58
    9
    0.58
    Activations Density 4.204%

    No Known Activations