© 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. 145702
    Prev
    Next
    INDEX
    Explanations

    common tradition

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

    API calls and compatibility

    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
     попы
    0.53
     возмо
    0.48
    editable
    0.48
    IST
    0.45
    nati
    0.44
    ↵
    0.44
     ath
    0.42
    ophys
    0.42
    閏
    0.41
    сто
    0.41
    POSITIVE LOGITS
     Lactobacillus
    0.57
     verlei
    0.54
     张
    0.52
     स्‍टार
    0.52
     प्रोटीन
    0.51
     长
    0.50
     专业
    0.50
     eksp
    0.49
    kast
    0.49
    গ্রাম
    0.49
    Activations Density 0.001%

    No Known Activations