© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1311
    Prev
    Next
    INDEX
    Explanations

    animal rescue and rehabilitation

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

    The neuron strongly activates on tokens referring to wildlife, animal species, and related ecological or biological entities.

    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
    驴
    -0.81
    错过
    -0.80
     heterosexual
    -0.75
    確認
    -0.74
     پلیس
    -0.73
    缤
    -0.73
    팜
    -0.72
    千萬
    -0.72
    Organizer
    -0.71
     पुर
    -0.71
    POSITIVE LOGITS
     rehab
    1.89
     rescue
    1.85
     rehabilitation
    1.83
     rescued
    1.64
     rehabilit
    1.58
     rescu
    1.50
     rehabilitate
    1.45
     rescues
    1.45
     Rescue
    1.40
    rescue
    1.39
    Activations Density 0.012%

    No Known Activations