© 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. 34-GEMMASCOPE-RES-131K
    4. 81076
    Prev
    Next
    INDEX
    Explanations

    sem- prefixed words

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

    The neuron responds strongly to any occurrence of the character sequence “sem” within a token.

    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
     suoi
    -0.80
    Kala
    -0.79
    Another
    -0.78
    Needless
    -0.77
     perguntou
    -0.77
    Escrito
    -0.76
    LOOKING
    -0.75
     mention
    -0.72
    puma
    -0.72
     Another
    -0.71
    POSITIVE LOGITS
     sem
    1.28
     Sem
    1.26
    Sem
    1.15
     SEM
    1.04
     semifinal
    1.01
    sem
    1.00
    SEM
    0.88
    Avatar
    0.88
    strated
    0.86
    onces
    0.86
    Activations Density 0.036%

    No Known Activations