© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39459
    Prev
    Next
    INDEX
    Explanations

    Feder, chromatograph, hypothalamus

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

    terms related to federal or governmental entities and institutions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron fires on occurrences of the substring “Feder” (e.g. in “Federated,” “Federally,” “Federations,” etc.).

    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
    "
    -4.31
     In
    -3.86
     For
    -3.80
     
    -3.34
     Only
    -3.28
    $
    -3.16
    h
    -3.16
    .
    -3.13
     If
    -2.98
    (
    -2.98
    POSITIVE LOGITS
    ⑊
    3.77
    ꯶
    3.41
     カップル
    3.41
    휀
    3.28
    ཫ
    3.22
     夜景
    3.20
    ꦤ
    3.17
     parachoque
    3.16
    
    3.16
    Ꮞ
    3.11
    Activations Density 0.013%

    No Known Activations