© 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. 73446
    Prev
    Next
    INDEX
    Explanations

    the following noun

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

    The neuron flags integer numerals (numeric tokens) 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_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
    Aggi
    -1.68
    ၚ
    -1.59
    Amical
    -1.56
    obvious
    -1.55
     delicioso
    -1.52
    趼
    -1.52
     tampoco
    -1.49
    rainian
    -1.49
    grazie
    -1.48
    regard
    -1.48
    POSITIVE LOGITS
    u
    1.97
    t
    1.83
    j
    1.66
     =
    1.65
    x
    1.59
     your
    1.59
    v
    1.57
     We
    1.55
    l
    1.55
        
    1.54
    Activations Density 0.078%

    No Known Activations