© 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. 73475
    Prev
    Next
    INDEX
    Explanations

    words starting with inf

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

    The neuron strongly activates on tokens containing the sequence “inf” (in any case), especially when it appears as the start of a word.

    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
    殽
    -2.63
    alakip
    -2.63
    Ⲉ
    -2.53
    mpagne
    -2.53
     zweiten
    -2.52
     gemeinsamen
    -2.50
     emphas
    -2.33
    汌
    -2.33
    🪆
    -2.31
     dritten
    -2.30
    POSITIVE LOGITS
    踅
    2.81
    会不会
    2.78
    です
    2.58
    ῞
    2.53
    u
    2.50
    ]
    2.50
     zewnętrzne
    2.48
     techniczne
    2.45
    简直
    2.44
     綠
    2.42
    Activations Density 0.009%

    No Known Activations