© 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. 58247
    Prev
    Next
    INDEX
    Explanations

    writing or recording information

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

    The neuron detects mentions of writing or journaling activities (e.g., words like “writing,” “journaling,” “wrote,” or “put it all in words”).

    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
     através
    -0.97
     THROUGH
    -0.97
    ică
    -0.89
    Zoom
    -0.89
    through
    -0.88
    ждает
    -0.88
     MISSING
    -0.88
     rano
    -0.87
    irn
    -0.87
    νος
    -0.86
    POSITIVE LOGITS
     down
    1.89
     on
    1.84
     in
    1.47
     out
    1.30
     onto
    1.13
    write
    1.11
     write
    1.08
     Write
    0.98
    ToFile
    0.97
     what
    0.95
    Activations Density 0.018%

    No Known Activations