© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 134065
    Prev
    Next
    INDEX
    Explanations

    here's followed by what or why

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

    detailed breakdown

    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
     WHILE
    0.43
     Zusatz
    0.43
     URLs
    0.42
    并
    0.42
     Corn
    0.41
     Palms
    0.41
     Ahl
    0.41
     URL
    0.40
     Ern
    0.40
     Arms
    0.40
    POSITIVE LOGITS
    what
    0.53
     how
    0.49
    ia
    0.48
    oqu
    0.47
    ow
    0.47
     cómo
    0.47
    াইলেন
    0.46
    wy
    0.46
    o
    0.46
     what
    0.46
    Activations Density 0.016%

    No Known Activations