© 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. 219181
    Prev
    Next
    INDEX
    Explanations

    actions and related descriptors

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

    disciplines, body

    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
    pct
    0.52
    bfc
    0.50
    dd
    0.49
    之后
    0.47
    dsp
    0.47
    mouseX
    0.47
    ',(
    0.47
    a
    0.47
     contested
    0.46
    rsp
    0.46
    POSITIVE LOGITS
     নিতান্ত
    0.52
     faibles
    0.50
     กู
    0.48
     ನೀರಿನ
    0.48
    IDO
    0.47
     positively
    0.47
     Pam
    0.46
     घड़ी
    0.46
     นา
    0.46
    圧力
    0.46
    Activations Density 0.001%

    No Known Activations