© 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. 22-GEMMASCOPE-RES-131K
    7. 72057
    Prev
    Next
    INDEX
    Explanations

    questions or descriptive phrases

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

    This neuron detects sentence- or line-initial tokens (i.e., the first word of a sentence or new line).

    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
     jazdy
    -1.56
    킁
    -1.55
    Ꮴ
    -1.55
    
    -1.53
     tunik
    -1.53
    
    -1.50
    rzost
    -1.48
    celotti
    -1.48
     tapete
    -1.47
    zestaw
    -1.47
    POSITIVE LOGITS
    te
    1.63
    im
    1.43
    y
    1.41
    in
    1.38
    ar
    1.37
    StatusCodes
    1.37
    u
    1.36
    am
    1.35
    .../
    1.34
    ant
    1.32
    Activations Density 0.041%

    No Known Activations