© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11277
    Prev
    Next
    INDEX
    Explanations

    utf-8 encoding

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

    the occurrence of the term “unicode.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ()">
    0.65
    会員
    0.60
    /");
    0.59
    讃
    0.59
     セット
    0.59
    /">
    0.58
    "};
    0.56
    )」
    0.55
    |$.
    0.55
    スイッチ
    0.55
    POSITIVE LOGITS
     kidn
    0.63
     haunted
    0.63
     competit
    0.59
     नाराज
    0.59
     kidnap
    0.57
     सज
    0.55
    醐
    0.55
     ಬಂದ
    0.54
     transport
    0.52
     advertis
    0.52
    Activations Density 0.000%

    No Known Activations