© 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. 100701
    Prev
    Next
    INDEX
    Explanations

    likelihood of an outcome

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

    The neuron spotlights comparative probability phrases—especially “more likely to” constructions often paired with numeric statistics.

    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
    𐄁
    -2.05
    珹
    -2.00
    ⤞
    -1.91
     monstruos
    -1.80
    síða
    -1.78
    髫
    -1.77
     eterno
    -1.72
     logique
    -1.70
     fieltro
    -1.68
     ciddi
    -1.66
    POSITIVE LOGITS
    2
    2.02
    4
    1.80
    8
    1.80
    X
    1.73
    时候
    1.64
     if
    1.59
    e
    1.55
    6
    1.52
    two
    1.46
    3
    1.46
    Activations Density 0.010%

    No Known Activations