© 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. 78920
    Prev
    Next
    INDEX
    Explanations

    colorful look

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

    correspondence and sources

    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
     réellement
    0.50
    是指
    0.49
    ныя
    0.45
     vitally
    0.42
    (*)
    0.41
     McGu
    0.40
     coeur
    0.40
     formulating
    0.39
     McKenzie
    0.39
     சிறி
    0.39
    POSITIVE LOGITS
    ्यूज
    0.52
    धू
    0.49
    の後
    0.47
     enclosure
    0.47
    अग
    0.46
    の子
    0.46
    அ
    0.45
    ax
    0.44
     سپر
    0.44
    つの
    0.43
    Activations Density 0.000%

    No Known Activations