© 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. 44541
    Prev
    Next
    INDEX
    Explanations

    css text alignment

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

    The neuron never fires—i.e. it is effectively “dead” and doesn’t detect any pattern in the input.

    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
    //
    -2.58
    ]
    -2.52
    _
    -2.39
    |
    -2.31
    f
    -2.30
    <em>
    -2.25
      
    -2.25
    h
    -2.22
    #
    -2.22
    r
    -2.19
    POSITIVE LOGITS
     rezultat
    2.11
    
    2.03
    ྥ
    1.88
    哢
    1.88
    鈁
    1.87
     filma
    1.85
     Minha
    1.81
     エントランス
    1.79
    ⸨
    1.78
     umo
    1.77
    Activations Density 0.001%

    No Known Activations