© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99365
    Prev
    Next
    INDEX
    Explanations

    history of, in recent

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

    The neuron responds to unusual non-English tokens and formatting markers—e.g. sequences of underscores, anonymized placeholders, or Japanese phrase fragments.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ৢ
    -2.77
    iſter
    -2.58
    螣
    -2.47
     of
    -2.36
    相关文章
    -2.27
    盦
    -2.27
    🪆
    -2.25
    秤
    -2.25
    
    -2.23
    痾
    -2.16
    POSITIVE LOGITS
    ↵
    2.84
    縂
    2.44
    5
    2.41
    淶
    2.33
     they
    2.31
     “(
    2.22
    ”.
    2.16
    on
    2.16
    ,’
    2.09
    ated
    2.08
    Activations Density 0.000%

    No Known Activations