© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103034
    Prev
    Next
    INDEX
    Explanations

    in order to deploy

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

    This neuron fires on the very first word of a new text segment—i.e. the initial, capitalized token at the start of a sentence or block.

    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
     also
    -2.47
     também
    -2.17
     také
    -1.73
     también
    -1.70
    也
    -1.63
     then
    -1.60
    也是
    -1.56
    thole
    -1.52
     też
    -1.52
     أفضل
    -1.52
    POSITIVE LOGITS
    ichtete
    1.70
    tanleria
    1.54
    According
    1.54
    Sometimes
    1.53
     provenientes
    1.52
    Following
    1.50
    Despite
    1.50
    When
    1.46
    While
    1.45
     getIntent
    1.45
    Activations Density 0.227%

    No Known Activations