© 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. 22-GEMMASCOPE-RES-131K
    4. 54364
    Prev
    Next
    INDEX
    Explanations

    git checkout branch

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

    This neuron detects mentions of Git branch and remote operations (e.g., commands like list, remote, branches, checkout, PR branch).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     disgruntled
    -1.37
     colocar
    -1.34
     captivating
    -1.33
     molte
    -1.30
     procedimento
    -1.30
    以外は
    -1.27
     sooo
    -1.27
     astounding
    -1.27
     flamboyant
    -1.27
    に入れる
    -1.25
    POSITIVE LOGITS
     by
    2.59
     with
    2.20
     in
    2.16
     just
    1.82
     at
    1.80
     using
    1.76
     for
    1.75
     through
    1.69
     from
    1.65
     even
    1.63
    Activations Density 0.201%

    No Known Activations