© 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. 25414
    Prev
    Next
    INDEX
    Explanations

    Q words and specific identifiers

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

    This neuron detects the opening of markup tags whose names begin with a numeric string (i.e. a “<” token immediately followed by digits).

    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
     if
    -1.30
    LEBR
    -1.27
     all
    -1.12
    NOTIFY
    -1.09
    ENAS
    -1.07
     Bretaña
    -1.06
    MANUEL
    -1.05
     tertawa
    -1.02
    ERICK
    -0.99
     their
    -0.98
    POSITIVE LOGITS
    儅
    1.14
    CIA
    1.03
    sandalia
    1.02
    饷
    1.02
    Continu
    1.02
     MAKES
    0.98
     تھے
    0.97
    品牌的
    0.97
    utilisons
    0.96
     vultures
    0.96
    Activations Density 0.000%

    No Known Activations