© 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. 109350
    Prev
    Next
    INDEX
    Explanations

    city pier pass Program guide digital download

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

    lists or code elements

    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
    داول
    0.46
    ιου
    0.45
     номера
    0.44
    业
    0.44
    ır
    0.43
    ালি
    0.42
    奘
    0.42
    応
    0.41
    的相关
    0.41
    veranst
    0.41
    POSITIVE LOGITS
     बताया
    0.54
    य
    0.54
     Sver
    0.51
     Eduardo
    0.47
     सचिन
    0.46
    ময়
    0.46
    lof
    0.45
     mucho
    0.45
     Only
    0.44
     Sachin
    0.44
    Activations Density 0.000%

    No Known Activations