© 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. 85436
    Prev
    Next
    INDEX
    Explanations

    paths and urls

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

    The neuron is primarily detecting slash characters ( “/” ) in code and text.

    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
    and
    -2.22
    Also
    -1.99
    which
    -1.91
     did
    -1.90
    </h2>
    -1.90
    Those
    -1.89
     went
    -1.84
    W
    -1.81
     allow
    -1.79
    that
    -1.79
    POSITIVE LOGITS
    ᐠ
    3.19
    
    2.22
     deliciously
    2.16
     exhilarating
    2.14
     strikingly
    2.09
    ㈲
    2.09
    ケモン
    2.08
     intric
    2.06
     delightfully
    2.05
    ⴽ
    2.05
    Activations Density 0.115%

    No Known Activations