© 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. 33016
    Prev
    Next
    INDEX
    Explanations

    outline of

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

    This neuron detects occurrences of the phrase “outline of” (i.e. the word “outline” often followed by “of”).

    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
    {
    -3.41
     you
    -3.00
    2
    -2.98
     to
    -2.66
    <
    -2.48
    </i>
    -2.34
    A
    -2.27
    食べられる
    -2.23
    </
    -2.22
    </td>
    -2.20
    POSITIVE LOGITS
     of
    3.19
    媖
    2.86
    ?"
    2.64
    媄
    2.56
    puestas
    2.55
    亊
    2.52
    鈊
    2.42
     eşofman
    2.38
     katk
    2.33
     hırka
    2.31
    Activations Density 0.003%

    No Known Activations