© 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. 53758
    Prev
    Next
    INDEX
    Explanations

    phrases about you, work, or money

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

    API access and built incrementally

    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
    sk
    0.47
    你会
    0.44
    ↵↵
    0.43
     preposition
    0.42
    chn
    0.42
     institution
    0.41
    valued
    0.41
     reformer
    0.41
     participatory
    0.41
    sh
    0.40
    POSITIVE LOGITS
    اویر
    0.53
    IENTS
    0.52
    тические
    0.51
     disparo
    0.51
    }\,
    0.49
     нём
    0.49
    ாதாரண
    0.48
     нагру
    0.48
    rául
    0.48
    فون
    0.48
    Activations Density 0.000%

    No Known Activations