© 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. 10-GEMMASCOPE-RES-131K
    7. 8534
    Prev
    Next
    INDEX
    Explanations

    location abbreviations

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

    The neuron flags the parenthesized numeric codes (and their surrounding parentheses) used in news‐wire datelines.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     که
    -2.22
    </i>
    -1.93
    )
    -1.92
     särskilt
    -1.91
    
    -1.84
    ؟
    -1.80
     bekannte
    -1.77
     ")";
    -1.76
    Pgina
    -1.75
     bestimmten
    -1.74
    POSITIVE LOGITS
     and
    2.47
     progrès
    1.77
     deliciously
    1.73
    猝
    1.70
    Our
    1.66
     nosso
    1.66
     нашей
    1.64
     nossa
    1.63
     impec
    1.63
     soooo
    1.60
    Activations Density 0.026%

    No Known Activations