© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15995
    Prev
    Next
    INDEX
    Explanations

    statistics calculate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     கரிம
    0.62
    POSIX
    0.61
    ☜
    0.61
    ሰ
    0.59
    siblings
    0.58
    서울
    0.57
     হাসপাত
    0.56
    உலகின்
    0.56
    新生
    0.56
    僻
    0.56
    POSITIVE LOGITS
     generous
    0.61
     generosity
    0.60
     make
    0.60
     assist
    0.58
     Diam
    0.58
     Live
    0.57
     apologize
    0.57
     stab
    0.56
     live
    0.56
     missionary
    0.55
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.