© 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. 26689
    Prev
    Next
    INDEX
    Explanations

    of course

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

    of course

    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
    el
    0.93
    त
    0.85
    }$.
    0.79
    ت
    0.77
    ك
    0.77
     a
    0.76
    0
    0.73
    er
    0.69
     y
    0.69
    fish
    0.69
    POSITIVE LOGITS
    '
    1.48
    ного
    0.95
    of
    0.88
    ные
    0.85
    ні
    0.84
    wegen
    0.83
    ных
    0.80
    was
    0.76
    し
    0.75
     đừng
    0.74
    Activations Density 0.161%

    No Known Activations