© 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. 112630
    Prev
    Next
    INDEX
    Explanations

    recycling, Indiana, suites, hands, valve

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

    rewrite instructions

    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
    ١
    0.50
    ]])
    0.49
    ]',
    0.49
     gloria
    0.49
     بک
    0.48
    \#
    0.47
    Includes
    0.47
    True
    0.46
     #
    0.46
    ;
    0.46
    POSITIVE LOGITS
    angen
    0.46
     跟
    0.46
    垻
    0.46
     लहान
    0.45
     書い
    0.45
     販売
    0.45
     與
    0.44
    сть
    0.44
    ﾍ
    0.44
     있으며
    0.44
    Activations Density 0.003%

    No Known Activations