© 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. 22445
    Prev
    Next
    INDEX
    Explanations

    Alumina CI, accompanied by

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

    purpose or intent

    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
    ívne
    0.43
     ­
    0.43
     दूसरा
    0.42
    õ
    0.42
    íž
    0.41
    ୈ
    0.41
     рождения
    0.40
    ſs
    0.40
    ukov
    0.40
    、
    0.39
    POSITIVE LOGITS
     Пара
    0.50
    添付
    0.50
     Мето
    0.49
     શિક્ષણ
    0.49
    🖍
    0.48
     vogue
    0.47
    PathDirectory
    0.47
     পদ্ধতির
    0.47
    DateFormat
    0.46
     جناب
    0.46
    Activations Density 0.000%

    No Known Activations