© 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. 68135
    Prev
    Next
    INDEX
    Explanations

    affirming authenticity

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

    The neuron selectively activates on occurrences of the word “real.”

    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
    ↵↵
    -1.91
     ſte
    -1.62
    哢
    -1.53
     '';
    -1.52
    釭
    -1.51
    狃
    -1.49
    激烈
    -1.48
     heyday
    -1.48
     ſy
    -1.48
     zodat
    -1.48
    POSITIVE LOGITS
    {
    1.91
    甜點
    1.82
     that
    1.76
    又は
    1.55
     when
    1.53
    but
    1.51
    羂
    1.47
     vieta
    1.41
    寕
    1.39
    湉
    1.37
    Activations Density 0.016%

    No Known Activations