© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 93477
    Prev
    Next
    INDEX
    Explanations

    boolean true/false flags

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

    The neuron doesn’t respond to any of the tokens shown—it appears to be inactive (“dead”) on these inputs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Following
    -1.40
    Although
    -1.40
    With
    -1.38
    Jahre
    -1.36
    Even
    -1.33
    。 
    -1.29
    Those
    -1.28
     kontinu
    -1.26
     what
    -1.24
    Two
    -1.23
    POSITIVE LOGITS
     
    1.48
    などは
    1.34
     trattano
    1.23
     rendono
    1.07
     opulent
    1.05
     flashy
    1.05
     &
    1.05
     vários
    1.02
     –
    1.02
    art
    1.02
    Activations Density 0.003%

    No Known Activations