© 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. 10-GEMMASCOPE-RES-131K
    7. 86621
    Prev
    Next
    INDEX
    Explanations

    source code definition

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

    The neuron activates on the uppercase label “SOURCE” (as used in code or document section headers).

    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
    ORIAL
    -1.67
    
    -1.65
     gefährlich
    -1.59
    ޞ
    -1.58
     ruinas
    -1.58
     fiume
    -1.57
     späteren
    -1.56
     bestehenden
    -1.52
     carreteras
    -1.52
     Moscú
    -1.51
    POSITIVE LOGITS
    .
    2.31
    </sup>
    1.93
    Should
    1.77
    SOURCE
    1.76
    ه
    1.75
    These
    1.66
    an
    1.66
    </td>
    1.65
    ,
    1.60
    We
    1.59
    Activations Density 0.016%

    No Known Activations