© 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. 124166
    Prev
    Next
    INDEX
    Explanations

    word followed by related word

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

    last few years

    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
     iyong
    0.49
     對
    0.48
     alleg
    0.47
     quantas
    0.47
     organelles
    0.47
     போர்
    0.47
     Bort
    0.47
     caramel
    0.47
     fels
    0.47
     Uyg
    0.46
    POSITIVE LOGITS
    JFrame
    0.44
    崩溃
    0.43
    本书
    0.40
    邝
    0.40
    <0xB7>
    0.39
     никак
    0.39
    自从
    0.39
    Dream
    0.38
    侃
    0.38
     ठाकुर
    0.38
    Activations Density 0.000%

    No Known Activations