© 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. 22-GEMMASCOPE-RES-131K
    7. 14931
    Prev
    Next
    INDEX
    Explanations

    questions starting with Q:

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

    The neuron is effectively inactive on these samples and does not consistently detect any particular token or 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
    
    -0.93
     harap
    -0.91
     Energía
    -0.88
    åter
    -0.88
     susu
    -0.88
    ⿱
    -0.88
    нциклопе
    -0.88
     Technique
    -0.87
     Proceso
    -0.87
     maksi
    -0.86
    POSITIVE LOGITS
    .;
    0.79
     leurs
    0.79
     opinions
    0.74
     Wahrheit
    0.72
    }_{\
    0.72
    atchi
    0.71
     opiniones
    0.70
     إليها
    0.70
     hielt
    0.70
     Diploma
    0.69
    Activations Density 0.000%

    No Known Activations