© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14868
    Prev
    Next
    INDEX
    Explanations

    do them

    np_acts-logits-general · gemini-2.5-flash-lite

    register / registry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    l
    0.60
     like
    0.52
    prepareStatement
    0.50
    tahun
    0.49
    t
    0.49
    ტ
    0.49
    ρ
    0.47
    h
    0.47
    v
    0.46
    :]
    0.46
    POSITIVE LOGITS
    ندان
    0.47
    छोटी
    0.47
    cloudinary
    0.47
     riguardo
    0.47
     Microscopy
    0.46
     marches
    0.46
    िसो
    0.46
    lipidemia
    0.45
     scanty
    0.44
     approche
    0.44
    Activations Density 0.000%

    No Known Activations