© 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. 10-GEMMASCOPE-RES-131K
    7. 100662
    Prev
    Next
    INDEX
    Explanations

    fixing, fixed, set, attached

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

    The neuron fires on occurrences of the “fix” root in various inflected forms (fixing, fixed, etc.).

    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
    ↵↵
    -3.20
    彞
    -2.70
    ༷
    -2.56
    鶿
    -2.50
    ܞ
    -2.44
     イエロー
    -2.33
    ᥀
    -2.33
    逦
    -2.27
    
    -2.22
    齶
    -2.22
    POSITIVE LOGITS
    in
    2.98
    h
    2.42
    ll
    2.31
     provocado
    2.31
    il
    2.27
     When
    2.20
    g
    2.17
     =
    2.08
    ?"
    2.03
    Polen
    2.02
    Activations Density 0.025%

    No Known Activations