© 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. 142339
    Prev
    Next
    INDEX
    Explanations

    not X, still X, must X

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

    little bit

    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
    íd
    0.51
     территориа
    0.49
    afka
    0.49
    进口
    0.48
    折扣
    0.47
    可用
    0.47
    <0x8A>
    0.46
    褐色
    0.46
     赵
    0.46
     محل
    0.45
    POSITIVE LOGITS
    MaxPooling
    0.47
    s
    0.47
    in
    0.47
     aerial
    0.45
     continuum
    0.44
    ی
    0.44
     inversion
    0.44
    あるいは
    0.44
    c
    0.43
     converting
    0.43
    Activations Density 0.001%

    No Known Activations