© 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. 234481
    Prev
    Next
    INDEX
    Explanations

    need this

    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
    怙
    0.54
    ра
    0.51
    ла
    0.51
    ر
    0.51
    σκ
    0.50
     Paz
    0.49
    ין
    0.48
    谗
    0.48
     frequ
    0.47
     juventud
    0.47
    POSITIVE LOGITS
     इसी
    0.50
     ऐसी
    0.48
     đêm
    0.44
    uild
    0.43
    arians
    0.43
    '
    0.43
     such
    0.42
    aries
    0.42
    aled
    0.42
    iche
    0.41
    Activations Density 0.001%

    No Known Activations