© 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. 66923
    Prev
    Next
    INDEX
    Explanations

    information about or on

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

    This neuron primarily fires on occurrences of the word “information.”

    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
    －－
    -1.75
     शुर
    -1.67
    ．．
    -1.66
    各自
    -1.52
     felicitación
    -1.49
     また
    -1.49
     three
    -1.48
    เกง
    -1.48
    sukienka
    -1.46
     You
    -1.45
    POSITIVE LOGITS
     nhưng
    1.82
    2
    1.65
    n
    1.63
     nossos
    1.62
    6
    1.59
    redientes
    1.56
    终究
    1.51
    睏
    1.51
    v
    1.51
     tetapi
    1.49
    Activations Density 0.049%

    No Known Activations