© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 202327
    Prev
    Next
    INDEX
    Explanations

    building products

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ocasiones
    0.51
    擞
    0.51
     sõ
    0.46
    暑
    0.45
    立場
    0.44
    ান্দ
    0.44
    त्मक
    0.43
    ழ
    0.43
     üret
    0.43
     Fakultas
    0.43
    POSITIVE LOGITS
    che
    0.59
    st
    0.57
    Paul
    0.53
    be
    0.52
    pro
    0.52
    lie
    0.51
    sea
    0.51
     או
    0.50
    Main
    0.50
    Y
    0.50
    Activations Density 0.003%

    No Known Activations