© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22957
    Prev
    Next
    INDEX
    Explanations

    motes dancing

    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
     estuary
    0.55
     señaló
    0.52
    oğlu
    0.51
     Española
    0.50
     fórm
    0.48
     oversaw
    0.48
    )-\
    0.47
     expressões
    0.47
    ૬
    0.47
    nR
    0.46
    POSITIVE LOGITS
    Title
    0.55
    Trashed
    0.46
    場合
    0.44
    Arkansas
    0.44
    上也
    0.43
    陶
    0.43
    פק
    0.42
    慝
    0.42
     टाइटल
    0.42
    試
    0.42
    Activations Density 0.002%

    No Known Activations