© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99544
    Prev
    Next
    INDEX
    Explanations

    fit in, into, or with

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

    The main thing this neuron does is spot occurrences of the word “fit” (including forms like “fits”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    aconda
    -0.90
    _{
    -0.88
    utriche
    -0.86
     dış
    -0.85
    Standort
    -0.85
    hadow
    -0.84
     presencia
    -0.83
    urel
    -0.83
    iron
    -0.82
     タオル
    -0.80
    POSITIVE LOGITS
     into
    2.39
     snug
    1.40
     the
    1.31
     Fits
    1.19
     within
    1.14
     vào
    1.07
     squarely
    1.05
     fit
    1.04
     neatly
    1.03
     onto
    1.02
    Activations Density 0.013%

    No Known Activations