© 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. 34-GEMMASCOPE-RES-131K
    7. 57118
    Prev
    Next
    INDEX
    Explanations

    of [noun/adjective]

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

    The neuron detects numeric tokens (measurements or counts) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     totalidad
    -0.98
     surroundings
    -0.98
     and
    -0.98
    ciers
    -0.98
     skies
    -0.97
     trenes
    -0.93
     totalité
    -0.93
    reys
    -0.92
    mographie
    -0.92
    SOA
    -0.89
    POSITIVE LOGITS
     some
    1.05
     certain
    0.95
     our
    0.93
    gadas
    0.88
     many
    0.86
     an
    0.85
     inconvénients
    0.82
     berkomunikasi
    0.82
     the
    0.82
    jaga
    0.82
    Activations Density 0.244%

    No Known Activations