© 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. 195641
    Prev
    Next
    INDEX
    Explanations

    measurements and demand

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

    describe me or explain why

    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
     చెందిన
    0.46
     likes
    0.46
    т
    0.46
    ט
    0.46
     peek
    0.45
    '].
    0.44
    ANS
    0.42
    ノル
    0.42
    ช่วง
    0.42
    ק
    0.42
    POSITIVE LOGITS
    दर्शी
    0.44
    tao
    0.41
     carbohydrates
    0.41
     حامل
    0.41
    導致
    0.41
    xyplot
    0.41
    opie
    0.40
    aundice
    0.40
    ciplinary
    0.40
    trajectory
    0.39
    Activations Density 0.001%

    No Known Activations