© 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. 181442
    Prev
    Next
    INDEX
    Explanations

    sanctuary, mountains, LGBT center

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

    space closed, increase students, and biopsy

    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
     જન્મ
    0.41
    简约
    0.41
    蕙
    0.39
     ضرور
    0.39
    จำเป็น
    0.39
    gunta
    0.38
    ্টন
    0.38
     اصحاب
    0.38
     తిరిగి
    0.38
     reorganize
    0.38
    POSITIVE LOGITS
     മു
    0.56
    argin
    0.55
     tady
    0.52
    み
    0.52
     tween
    0.49
    t
    0.48
     Ultraviolet
    0.47
    0.47
     colis
    0.46
     altre
    0.46
    Activations Density 0.000%

    No Known Activations