© 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-16K
    7. 7260
    Prev
    Next
    INDEX
    Explanations

    floaters

    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_16k_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
    Shop
    0.50
    Conta
    0.49
    Rounded
    0.48
     organizada
    0.45
    '
    0.44
    Hound
    0.44
    Whole
    0.42
    Grunge
    0.42
    Retrie
    0.42
    Purchase
    0.41
    POSITIVE LOGITS
    т
    0.54
     it
    0.51
     தாம
    0.51
    it
    0.50
     विकार
    0.49
     mute
    0.48
     an
    0.47
     excretion
    0.47
    ने
    0.47
     battle
    0.47
    Activations Density 0.029%

    No Known Activations