© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 202757
    Prev
    Next
    INDEX
    Explanations

    technical nouns and associated actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     problèmes
    0.46
     ,
    0.46
    '
    0.45
     nêu
    0.43
     sucess
    0.43
     \
    0.43
     doc
    0.43
    icul
    0.43
     $\
    0.42
    实际上
    0.41
    POSITIVE LOGITS
     combinatie
    0.51
    Trailing
    0.47
    Ignoring
    0.44
    Oct
    0.43
    Harris
    0.42
    achtig
    0.41
     खिलाड़ी
    0.41
    footed
    0.41
     ИП
    0.40
    畊
    0.40
    Activations Density 0.005%

    No Known Activations