© 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. 66880
    Prev
    Next
    INDEX
    Explanations

    special characters and encoding errors

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

    The neuron fires on occurrences of the garbled “â” character (i.e. mojibake or malformed non-ASCII sequences).

    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
     Then
    -2.83
     แล้ว
    -2.28
     Also
    -2.27
    who
    -2.27
     is
    -2.27
     Notably
    -2.25
     It
    -2.19
     ก็
    -2.17
    ㉗
    -2.16
    n
    -2.14
    POSITIVE LOGITS
    餮
    2.69
    ⸰
    2.44
    鹟
    2.36
    龱
    2.33
    viembre
    2.33
    anthene
    2.30
     suami
    2.30
                    
    2.28
    桖
    2.25
    廰
    2.25
    Activations Density 0.005%

    No Known Activations