© 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. 100506
    Prev
    Next
    INDEX
    Explanations

    out there

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

    This neuron strongly activates on occurrences of the phrase “out there.”

    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
     this
    -2.20
    The
    -1.67
     our
    -1.66
    if
    -1.59
     or
    -1.45
    ="
    -1.43
    It
    -1.41
     یا
    -1.38
     these
    -1.38
    i
    -1.33
    POSITIVE LOGITS
     THOSE
    1.77
    戋
    1.70
     EVEN
    1.67
     to
    1.62
    ’
    1.56
    "{\
    1.54
    〬
    1.48
     SOME
    1.45
    selben
    1.45
    清醒
    1.44
    Activations Density 0.009%

    No Known Activations