© 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. 4384
    Prev
    Next
    INDEX
    Explanations

    Midwest Tape

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

    The neuron fires on names and terms associated with library institutions, services, and related proper nouns.

    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
    Idade
    -0.84
     wysokość
    -0.82
    睬
    -0.72
     PLWABN
    -0.71
    Rejected
    -0.69
    ⛩
    -0.69
     Careers
    -0.69
     generating
    -0.67
     gâ
    -0.66
    Discard
    -0.66
    POSITIVE LOGITS
     Deposit
    0.90
    Ợ
    0.87
    Deposit
    0.86
     deposit
    0.85
     
    0.82
     borrower
    0.79
    metto
    0.78
     deposits
    0.77
    HttpException
    0.77
    deutschland
    0.74
    Activations Density 0.031%

    No Known Activations