© 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. 35640
    Prev
    Next
    INDEX
    Explanations

    our way, the odds, seems to

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

    integrating well, my training data

    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
    </h4>
    0.46
    :
    0.46
    hereafter
    0.43
     The
    0.43
    dock
    0.42
    provided
    0.42
    t
    0.41
     represented
    0.40
    ↵↵
    0.40
    proposed
    0.40
    POSITIVE LOGITS
     невозможно
    0.54
     actuaciones
    0.53
    াজিক
    0.51
     फिजिक्स
    0.47
    綪
    0.47
     inexist
    0.46
     કરીએ
    0.46
    Ⲉ
    0.46
    互动
    0.45
     rotacao
    0.45
    Activations Density 0.000%

    No Known Activations