© 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. 21482
    Prev
    Next
    INDEX
    Explanations

    allowed items or values

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

    The neuron fires strongly on occurrences of the word “allowed,” i.e. when the text is describing permitted or allowable options/values.

    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
     protagonistas
    -2.23
    矬
    -2.19
     extré
    -2.13
    缑
    -2.02
    翃
    -1.97
     bluza
    -1.91
     réservoir
    -1.91
    棡
    -1.84
    يارات
    -1.83
     fotografias
    -1.83
    POSITIVE LOGITS
    l
    2.50
     However
    2.47
    4
    2.16
    7
    2.08
    5
    1.96
    at
    1.95
     of
    1.93
    8
    1.90
     These
    1.89
     Therefore
    1.89
    Activations Density 0.010%

    No Known Activations