© 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. 101198
    Prev
    Next
    INDEX
    Explanations

    `mojito`, `Monkeys`, `signal`, `CA`, `reading`

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

    print statement examples

    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
    یک
    0.50
    保持
    0.50
    зан
    0.48
    μβ
    0.48
    惜
    0.48
    ุง
    0.47
    سی
    0.47
     informado
    0.47
    瑆
    0.46
    जिया
    0.45
    POSITIVE LOGITS
    bz
    0.51
    coni
    0.47
    comps
    0.47
    bore
    0.46
    P
    0.45
    oura
    0.45
    gro
    0.45
    celi
    0.44
    cof
    0.44
    fashioned
    0.43
    Activations Density 0.000%

    No Known Activations