© 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. 77783
    Prev
    Next
    INDEX
    Explanations

    words starting with fore

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

    This neuron detects the string “Fore” at the start of words (i.e. the prefix “fore-”).

    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
     raids
    -0.76
    recall
    -0.75
     unmarried
    -0.73
     Asp
    -0.71
    ㄷ
    -0.70
    Spaces
    -0.69
     クレ
    -0.69
    クリア
    -0.69
    IFIC
    -0.69
    saan
    -0.68
    POSITIVE LOGITS
     fore
    1.88
     Fore
    1.76
    Fore
    1.73
     FORE
    1.55
    fore
    1.44
    FORE
    1.27
     forearm
    1.16
     Fores
    1.12
    fores
    1.09
     fores
    1.06
    Activations Density 0.015%

    No Known Activations