© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 170607
    Prev
    Next
    INDEX
    Explanations

    favourite pieces

    np_acts-logits-general · gemini-2.5-flash-lite

    technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Innovation
    0.55
     juara
    0.51
    innovation
    0.49
    Innovation
    0.47
     bravery
    0.46
     จ
    0.46
     trening
    0.46
     exib
    0.46
     fenomen
    0.45
     ako
    0.45
    POSITIVE LOGITS
    énagement
    0.45
     giám
    0.44
    螺
    0.43
    ียด
    0.42
    댁
    0.42
    íses
    0.42
     hạn
    0.42
     chậm
    0.41
    া
    0.41
    뱉
    0.41
    Activations Density 0.001%

    No Known Activations