© 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. 8165
    Prev
    Next
    INDEX
    Explanations

    ruminants, swollen, Michele, inflated, CRP

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

    The neuron primarily detects the word "ruminants" and sometimes responds to words related to physical swelling.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    -3.05
     they
    -2.64
    ING
    -2.63
    }\
    -2.59
    逦
    -2.52
     But
    -2.41
    ている
    -2.38
     are
    -2.34
    摁
    -2.25
     algunos
    -2.19
    POSITIVE LOGITS
    ان
    3.17
    ～～～
    2.73
    ～～～～
    2.70
    ～～
    2.55
     valentín
    2.45
    
    2.34
    酲
    2.30
    橚
    2.28
    蘗
    2.23
    蟶
    2.20
    Activations Density 0.006%

    No Known Activations