© 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. 34-GEMMASCOPE-RES-131K
    7. 79094
    Prev
    Next
    INDEX
    Explanations

    legal or code citations

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

    The neuron responds to descriptions of violent crime or gruesome acts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    atise
    -0.81
    принима
    -0.78
     还
    -0.76
     corpi
    -0.75
     feeble
    -0.75
     schönen
    -0.73
     asiática
    -0.73
    橡
    -0.72
     besonderen
    -0.72
     vague
    -0.72
    POSITIVE LOGITS
     ment
    1.04
    NaN
    0.94
     ing
    0.89
    ຳ
    0.86
    的文件
    0.86
     ചെയ
    0.85
    足
    0.85
    璃
    0.85
    ้าม
    0.84
     loginUser
    0.84
    Activations Density 0.030%

    No Known Activations