© 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. 33094
    Prev
    Next
    INDEX
    Explanations

    programming syntax and commands

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

    The neuron fires on very short alphabetic tokens (two‐ or three‐letter “words”).

    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
    uschen
    -0.91
    психо
    -0.87
    ϳ
    -0.84
     pries
    -0.84
     externes
    -0.83
    Вар
    -0.82
    ærke
    -0.81
     Efek
    -0.81
    REFUND
    -0.81
     JMenuItem
    -0.80
    POSITIVE LOGITS
    {\
    0.97
     '
    0.88
     name
    0.85
    DropColumn
    0.84
    }_{
    0.84
    এ
    0.84
    Ehrungen
    0.84
     women
    0.81
    V
    0.81
    _{
    0.80
    Activations Density 0.071%

    No Known Activations