© 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. 134849
    Prev
    Next
    INDEX
    Explanations

    thus we

    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
    姆斯
    0.49
    اك
    0.49
    环境保护
    0.48
    屼
    0.48
    ੂੰ
    0.47
    阿
    0.46
     Analysis
    0.46
    ปล่อย
    0.46
     Attempt
    0.45
    ם
    0.45
    POSITIVE LOGITS
    ర్థిక
    0.49
     boardroom
    0.47
    /***
    0.46
     phonetic
    0.45
    >>&
    0.45
     নিদর্শন
    0.45
     telefone
    0.43
     founded
    0.43
     jigsaw
    0.43
     wooded
    0.42
    Activations Density 0.000%

    No Known Activations