© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13550
    Prev
    Next
    INDEX
    Explanations

    muttering, dissemination, Mutembo

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

    until New

    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_16k_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
    笘
    0.58
     règlement
    0.50
    。『
    0.50
    。“
    0.49
    ле
    0.49
    参数向量
    0.48
    。「
    0.46
    枧
    0.46
    纱
    0.45
    䚯
    0.45
    POSITIVE LOGITS
    ardon
    0.54
     pura
    0.48
    revolution
    0.47
    etre
    0.47
    itere
    0.46
    stands
    0.46
     precipit
    0.45
    assim
    0.45
    äng
    0.44
    ordano
    0.43
    Activations Density 0.015%

    No Known Activations