© 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. 150848
    Prev
    Next
    INDEX
    Explanations

    average calculation description

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

    prevents most

    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
    Dob
    0.49
     الرا
    0.44
     plufieurs
    0.43
    biz
    0.41
     предложения
    0.41
     ainfi
    0.41
    sede
    0.41
    ຝ
    0.41
    business
    0.41
     tronc
    0.41
    POSITIVE LOGITS
     half
    0.44
     stability
    0.43
     größ
    0.41
    稳定
    0.39
     Regression
    0.39
    稳定性
    0.39
    <!
    0.38
     Cambodia
    0.38
     life
    0.38
     stable
    0.38
    Activations Density 0.000%

    No Known Activations