© 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. 34102
    Prev
    Next
    INDEX
    Explanations

    questions and specific terms

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

    The main thing this neuron does is detect the forward-slash character (“/”).

    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
    を
    -1.63
     inay
    -1.46
    そして
    -1.39
     verrez
    -1.38
     ALLA
    -1.37
     navigazione
    -1.35
    elegant
    -1.34
    ERICAN
    -1.34
    1
    -1.30
    ⿵
    -1.29
    POSITIVE LOGITS
    1.40
     Currently
    1.34
    </em>
    1.32
    のでしょう
    1.30
     If
    1.30
     _
    1.29
     Sometimes
    1.29
    After
    1.28
     ersten
    1.26
     With
    1.25
    Activations Density 0.000%

    No Known Activations