© 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. 124233
    Prev
    Next
    INDEX
    Explanations

    chapters, default, cover

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

    introduction, definition, or explanation

    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
    t
    0.55
    mk
    0.51
    g
    0.49
     अगली
    0.48
     परीक्षा
    0.48
    Gx
    0.47
    iol
    0.46
     गर्नु
    0.46
    river
    0.46
     Geç
    0.46
    POSITIVE LOGITS
    疑
    0.49
    在该
    0.45
     вероят
    0.44
    飏
    0.44
    zustellen
    0.43
     más
    0.42
    kenalkan
    0.41
     wahrscheinlich
    0.41
     sugars
    0.41
    üedad
    0.40
    Activations Density 0.001%

    No Known Activations