© 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. 25755
    Prev
    Next
    INDEX
    Explanations

    C2090-600 test

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

    incompleteness / completeness

    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
    하고
    0.48
    驄
    0.46
    utie
    0.46
    交换
    0.45
    o
    0.45
    échange
    0.44
    带
    0.44
    asiswa
    0.43
    otricha
    0.42
    TextChanged
    0.42
    POSITIVE LOGITS
     nitride
    0.55
     explanatory
    0.52
     ܗ
    0.52
     Aquaculture
    0.52
     antibacterial
    0.52
    内容は
    0.51
     Skipper
    0.50
     Freitas
    0.50
     shouldn
    0.50
     nitrite
    0.49
    Activations Density 0.000%

    No Known Activations