© 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. 163543
    Prev
    Next
    INDEX
    Explanations

    above for

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

    Email, designing, familiar, small

    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
    們
    0.44
     그녀
    0.44
     শপথ
    0.43
    殞
    0.43
    െങ്കില്‍
    0.42
    対流
    0.41
     乾燥
    0.41
     זאת
    0.41
     দূতাবাসের
    0.41
     впечат
    0.40
    POSITIVE LOGITS
    +
    0.55
    3
    0.53
    builder
    0.52
    T
    0.52
    7
    0.51
    و
    0.51
    db
    0.49
    at
    0.48
    ram
    0.48
    am
    0.47
    Activations Density 0.008%

    No Known Activations