© 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. 34-GEMMASCOPE-RES-131K
    7. 92446
    Prev
    Next
    INDEX
    Explanations

    place of birth, placeholders, placemarks

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

    The neuron fires on occurrences of the token “place” (including “Place,” “place-holder,” etc.), i.e. it detects the word “place” (often in placeholder or hyphenated form).

    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
     ret
    -0.79
     ambientes
    -0.79
    nhung
    -0.78
    清晰
    -0.76
    alleries
    -0.74
    HNO
    -0.73
    曜
    -0.72
    Ret
    -0.71
     ५
    -0.71
     secolo
    -0.70
    POSITIVE LOGITS
    ment
    1.02
    mats
    0.93
    holders
    0.92
    holder
    0.91
     placement
    0.89
    making
    0.86
    Holder
    0.86
     attachment
    0.85
    hold
    0.83
    ogen
    0.82
    Activations Density 0.018%

    No Known Activations