© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205147
    Prev
    Next
    INDEX
    Explanations

    . after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ς
    0.51
     realizing
    0.50
    ের
    0.45
    mathrm
    0.44
     άλλ
    0.43
     Petroleum
    0.42
     characterizing
    0.42
     recognizing
    0.41
     শিক্ষার্থীরা
    0.41
    紝
    0.40
    POSITIVE LOGITS
    BackgroundHelper
    0.54
    asti
    0.50
    ]++;
    0.46
     excl
    0.46
    malign
    0.45
    jo
    0.45
    ㄺ
    0.44
    t
    0.44
    ActionListener
    0.43
    trumpet
    0.43
    Activations Density 0.004%

    No Known Activations