© 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. 10-GEMMASCOPE-RES-131K
    7. 84177
    Prev
    Next
    INDEX
    Explanations

    recording logs and details

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

    The neuron activates on words and phrases referring to recording, logging, or noting data (e.g. record, recorded, recording, log).

    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
     autres
    -1.43
     other
    -1.34
     OTHER
    -1.26
     I
    -1.26
     andere
    -1.14
     autre
    -1.14
    其他
    -1.13
    Out
    -1.07
    C
    -1.05
     otros
    -1.05
    POSITIVE LOGITS
    ToFile
    1.19
     Anſ
    1.18
    ppich
    1.16
     Ländern
    1.14
     Anhäng
    1.13
    recorder
    1.13
     either
    1.13
    後記
    1.13
    IsNot
    1.13
     damaligen
    1.12
    Activations Density 0.181%

    No Known Activations