© 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. 33348
    Prev
    Next
    INDEX
    Explanations

    initialisms with periods

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

    This neuron detects sequences of single uppercase letters (often followed by periods) used as initials or abbreviations.

    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
     in
    -1.17
    াই
    -1.15
     аккура
    -1.12
     прошли
    -1.12
    jména
    -1.11
    が
    -1.09
     things
    -1.08
    Suerte
    -1.07
    Onze
    -1.07
    Filosof
    -1.06
    POSITIVE LOGITS
    場合には
    1.16
     العديد
    1.11
    iv
    1.09
     Frankrijk
    1.08
     некоторые
    1.04
    os
    1.03
    ut
    1.02
    ˗
    1.02
    的一些
    1.02
    alité
    1.02
    Activations Density 0.032%

    No Known Activations