© 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. 11501
    Prev
    Next
    INDEX
    Explanations

    interactions with peers

    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
    use
    0.59
     Man
    0.53
    request
    0.53
    nin
    0.52
    se
    0.52
     Per
    0.52
    last
    0.51
    ת
    0.49
    is
    0.49
    tax
    0.49
    POSITIVE LOGITS
     peers
    0.68
     ότι
    0.58
     که
    0.58
    с
    0.57
     classmates
    0.53
    ため
    0.52
     classmate
    0.52
    ському
    0.49
    으로부터
    0.49
    훗
    0.49
    Activations Density 0.003%

    No Known Activations