© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 61108
    Prev
    Next
    INDEX
    Explanations

    ruthless and relentless descriptions

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

    The neuron fires strongly on adjectives conveying extreme harshness or cruelty (e.g., “ruthless,” “relentless”).

    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
     förstå
    -1.86
    geſ
    -1.81
     gemens
    -1.72
    thenburg
    -1.68
     dotyczące
    -1.67
    jęcie
    -1.63
    国庆
    -1.59
    侷
    -1.59
    César
    -1.59
     cumbersome
    -1.57
    POSITIVE LOGITS
    ly
    2.08
     is
    2.00
     you
    1.88
     actuellement
    1.86
    1
    1.83
     relentless
    1.73
    7
    1.66
    尤其
    1.58
    to
    1.57
    6
    1.55
    Activations Density 0.019%

    No Known Activations