© 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. 15161
    Prev
    Next
    INDEX
    Explanations

    new code initialization

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

    The neuron fires on numeric literal tokens (e.g. integer or floating‐point constants).

    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
     alojamientos
    -1.39
     bocetos
    -1.34
    ⚢
    -1.33
    ANSAS
    -1.28
     tille
    -1.27
     enfermera
    -1.23
     preparada
    -1.23
     opini
    -1.23
     sonriente
    -1.22
     acoged
    -1.21
    POSITIVE LOGITS
     of
    2.30
     from
    1.64
    The
    1.53
     are
    1.52
     that
    1.50
     what
    1.45
     It
    1.41
     also
    1.36
    What
    1.34
     Also
    1.27
    Activations Density 0.010%

    No Known Activations