© 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. 223007
    Prev
    Next
    INDEX
    Explanations

    the followed by title nouns

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

    The followed by nouns

    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
    ü
    0.52
    {
    0.47
    eler
    0.46
    eds
    0.46
    ЛЕ
    0.45
    世界上
    0.44
    ி
    0.44
    י
    0.44
    م
    0.43
    ert
    0.43
    POSITIVE LOGITS
     retailing
    0.42
     jejich
    0.41
    大家
    0.40
     Ngf
    0.39
    而在
    0.39
     gleaned
    0.39
     včetně
    0.39
     SPSS
    0.38
     presenting
    0.38
     vooral
    0.38
    Activations Density 0.010%

    No Known Activations