© 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. 25811
    Prev
    Next
    INDEX
    Explanations

    questions and numbered lists

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

    The neuron selectively fires on code identifier tokens (e.g. quoted symbols and variable names) rather than ordinary prose.

    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
     they
    -1.23
     enkele
    -1.05
    Gruss
    -1.03
    楽しんで
    -1.02
    必要な
    -1.01
     ongeveer
    -1.00
     selben
    -0.99
    🕗
    -0.98
    benar
    -0.97
    ramo
    -0.96
    POSITIVE LOGITS
    🤓
    1.09
     }],
    1.06
    &
    1.04
     maman
    1.02
     */;
    1.00
     menit
    0.99
     arabe
    0.95
    ǁ
    0.94
    
    0.94
    self
    0.93
    Activations Density 0.000%

    No Known Activations