© 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. 22-GEMMASCOPE-RES-131K
    7. 33613
    Prev
    Next
    INDEX
    Explanations

    code snippets and tags

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

    This neuron never activates on any of the shown tokens—i.e. it’s effectively a “dead” neuron that doesn’t detect any pattern here.

    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
    ナメント
    -1.16
     jesu
    -1.06
     karde
    -1.05
    ЕНЬ
    -1.04
    мана
    -1.04
     optik
    -1.04
    bestimm
    -1.03
    ऎ
    -1.02
    +:+
    -1.02
     colch
    -1.01
    POSITIVE LOGITS
     again
    1.07
     more
    0.99
     is
    0.96
    1
    0.88
     "
    0.88
       
    0.88
    7
    0.88
    3
    0.88
     protože
    0.85
    9
    0.84
    Activations Density 0.012%

    No Known Activations