© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41323
    Prev
    Next
    INDEX
    Explanations

    liquefied petroleum

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

    past tense verbs, particularly those ending with 'ed'.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron flags past‐action word forms—English past or past‐participle “–ed” verbs and their Japanese equivalents (e.g. “しました,” “誤,” 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
    )");
    
    -2.02
    melons
    -1.74
    ση
    -1.70
    byes
    -1.69
    >");
    
    -1.65
    alties
    -1.63
     shur
    -1.63
    ጴ
    -1.59
    fordshire
    -1.59
    ');
    
    -1.59
    POSITIVE LOGITS
     from
    2.11
     like
    1.88
     based
    1.84
    なんだろう
    1.71
    This
    1.69
    nitř
    1.67
    '
    1.66
     other
    1.65
    していて
    1.64
    していました
    1.63
    Activations Density 0.004%

    No Known Activations