© 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. 205595
    Prev
    Next
    INDEX
    Explanations

    options, questions, or lists

    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
    സ്ഥാന
    0.52
     nCenters
    0.51
    జేపీ
    0.50
     étudié
    0.48
     Fulbright
    0.48
     isEqual
    0.47
    InitFlag
    0.47
    ỉnh
    0.47
    𝐍
    0.47
    $\--
    0.47
    POSITIVE LOGITS
    m
    0.46
    mat
    0.45
    마
    0.45
    元
    0.42
    狂
    0.42
    ਰੇ
    0.41
    c
    0.41
     supplies
    0.41
    는
    0.40
    ზე
    0.40
    Activations Density 0.004%

    No Known Activations