© 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. 122344
    Prev
    Next
    INDEX
    Explanations

    coming right up

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

    Stop Guessing, Start Growing

    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
     hemisph
    0.50
    coded
    0.48
     quantitative
    0.46
    partum
    0.46
    T
    0.46
     reproduced
    0.45
    adjusted
    0.45
     legislative
    0.45
     Precambrian
    0.45
    genus
    0.45
    POSITIVE LOGITS
     LikeLike
    0.52
     аккумуля
    0.51
    ظمة
    0.51
     则
    0.51
    шчы
    0.50
     رست
    0.50
    tır
    0.49
     اكتب
    0.48
    వచ్చు
    0.48
    群众
    0.47
    Activations Density 0.001%

    No Known Activations