© 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. 186496
    Prev
    Next
    INDEX
    Explanations

    various items

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

    various languages

    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
    ar
    0.42
    er
    0.40
    ટ
    0.39
    als
    0.39
    -
    0.38
    with
    0.37
    Forever
    0.37
    o
    0.37
    ay
    0.36
    u
    0.36
    POSITIVE LOGITS
     çeşitli
    0.55
     ಕೆಲವು
    0.51
    いくつかの
    0.49
     niektor
    0.47
     sejumlah
    0.47
     مختلف
    0.46
     verschiedenen
    0.46
     zowel
    0.45
     বেশকিছু
    0.45
     различных
    0.45
    Activations Density 0.000%

    No Known Activations