© 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. 245750
    Prev
    Next
    INDEX
    Explanations

    fit, Woman, owes, Reads

    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
     methods
    0.45
     методов
    0.43
     devised
    0.43
     extractive
    0.42
    疫
    0.42
     distortion
    0.41
    Chart
    0.41
     包括
    0.41
     Projection
    0.40
     from
    0.40
    POSITIVE LOGITS
     nouveaux
    0.53
    ごはん
    0.51
    几天
    0.49
    を購入
    0.48
    噌
    0.47
    ﻙ
    0.46
     novia
    0.46
    买了
    0.46
    월
    0.46
     ನಿಮ್ಮ
    0.45
    Activations Density 0.003%

    No Known Activations