© 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. 72292
    Prev
    Next
    INDEX
    Explanations

    words starting with fl

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

    The neuron is activated by the two‐letter sequence “Fl,” i.e. it spots the character bigram “Fl” at the start of words.

    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
    i
    -2.63
    aaaa
    -2.58
    aaa
    -2.42
    aan
    -2.36
    اً
    -2.34
    which
    -2.33
    e
    -2.28
    鬟
    -2.16
    胧
    -2.14
     wich
    -2.09
    POSITIVE LOGITS
     It
    2.23
    In
    2.22
     Because
    2.14
    öpfer
    2.06
    ászló
    2.02
     简介
    2.02
    もちろん
    2.00
     \&
    1.98
    On
    1.95
    There
    1.92
    Activations Density 0.101%

    No Known Activations