© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 69114
    Prev
    Next
    INDEX
    Explanations

    numbers starting with 1, 2, 9, -, L, Q, % or sea

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

    The neuron does not respond to any tokens—it never activates for any pattern.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    another
    -0.84
    がある
    -0.82
    фар
    -0.81
    colato
    -0.80
     Practi
    -0.80
     ciel
    -0.79
     chien
    -0.79
    optical
    -0.78
     iets
    -0.78
     ガーデン
    -0.78
    POSITIVE LOGITS
     svolge
    0.96
    弊社
    0.92
    ociação
    0.92
     過
    0.90
    ými
    0.88
     activ
    0.87
    guantes
    0.84
     arbeitet
    0.83
     zumindest
    0.83
     Bibliothek
    0.83
    Activations Density 0.000%

    No Known Activations