© 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. 39684
    Prev
    Next
    INDEX
    Explanations

    An ABC

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

    biased decisions or incorrect lists

    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
    บัน
    0.46
    Texto
    0.45
    晓
    0.41
    妤
    0.41
    法轮
    0.41
     acute
    0.40
     문
    0.39
     ג
    0.39
     erotic
    0.39
    急性
    0.39
    POSITIVE LOGITS
    you
    0.54
    os
    0.53
    we
    0.49
    each
    0.46
    that
    0.45
    creating
    0.45
    needed
    0.45
    remember
    0.45
    zo
    0.44
    tee
    0.44
    Activations Density 0.000%

    No Known Activations