© 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. 236273
    Prev
    Next
    INDEX
    Explanations

    last eight quarters

    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
    ѕ
    0.48
    nl
    0.47
    iston
    0.44
    yl
    0.42
    umu
    0.42
    gl
    0.41
    wl
    0.41
    prayer
    0.40
    .\
    0.40
    ⊕
    0.40
    POSITIVE LOGITS
     fomentar
    0.52
    はその
    0.52
     efectuar
    0.51
     únicamente
    0.50
     practicar
    0.48
    让人
    0.47
     Vorteil
    0.47
     hacerlo
    0.47
    ホーム
    0.47
     zumindest
    0.47
    Activations Density 0.001%

    No Known Activations