© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27859
    Prev
    Next
    INDEX
    Explanations

    variable declarations

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

    The neuron flags programming‐language syntax—e.g. function names, variable names, parentheses and other code tokens—marking bits of source code.

    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
     bilder
    -1.05
     Pacífico
    -1.00
     м
    -0.99
    isierung
    -0.99
    izing
    -0.98
     Союза
    -0.98
    henswürdigkeiten
    -0.97
    );
    -0.96
    < 
    -0.96
    häuse
    -0.95
    POSITIVE LOGITS
    сумка
    1.13
     it
    1.10
     éstos
    1.07
     Formerly
    1.02
     perdón
    1.02
     Betrachtung
    1.01
    當時
    1.01
     jezelf
    1.00
    它們
    1.00
     rhod
    0.99
    Activations Density 0.004%

    No Known Activations