© 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. 65394
    Prev
    Next
    INDEX
    Explanations

    file deletion commands

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

    The neuron fires on any token containing numeric digits—that is, it detects numeric literals or numbers embedded in 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
    </b>
    -1.24
    ento
    -1.15
    ↵↵↵
    -1.14
                
    -1.13
    </strong>
    -1.09
    @
    -1.07
     their
    -1.07
     urusan
    -1.06
     for
    -1.05
            
    -1.05
    POSITIVE LOGITS
     unangemessene
    1.17
     hidratante
    1.15
     pokud
    1.13
    planetary
    1.09
     nếu
    1.08
     celebridades
    1.06
     nije
    1.06
    IfExists
    1.04
    囔
    1.03
     acceptez
    1.02
    Activations Density 0.013%

    No Known Activations