© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56158
    Prev
    Next
    INDEX
    Explanations

    early February 2024

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    C
    0.63
    L
    0.59
    N
    0.56
    J
    0.52
    Ba
    0.51
    pets
    0.51
    es
    0.50
    and
    0.50
    D
    0.50
    Flying
    0.50
    POSITIVE LOGITS
     사회
    0.54
     scrapped
    0.52
    쩡
    0.51
     ഘ
    0.50
    🛡
    0.47
     vertebra
    0.46
    AWSJavaScriptSDK
    0.46
     tireless
    0.46
     nutty
    0.45
     legislator
    0.45
    Activations Density 0.000%

    No Known Activations