© 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. 134950
    Prev
    Next
    INDEX
    Explanations

    steering committees

    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
    主义
    0.51
     اللغه
    0.46
    岦
    0.45
     вулка
    0.45
    鿆
    0.44
    istán
    0.44
    碐
    0.44
    绫
    0.43
     ನೀವು
    0.43
     Después
    0.43
    POSITIVE LOGITS
    モチ
    0.49
    ¶
    0.48
    更
    0.47
    ’’
    0.46
    arit
    0.46
     refinancing
    0.45
     livelihood
    0.45
     repayment
    0.45
     regno
    0.44
    }
    0.44
    Activations Density 0.004%

    No Known Activations