© 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. 34-GEMMASCOPE-RES-131K
    7. 47828
    Prev
    Next
    INDEX
    Explanations

    said

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

    The neuron responds to common English idiomatic commentary phrases—especially “something to be said for…” and “easier said than done.”

    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
    ANTLR
    -0.88
    Ȁ
    -0.88
    卖家
    -0.85
    厂商
    -0.84
     หนัง
    -0.82
     fournisseur
    -0.82
    hows
    -0.82
     rescate
    -0.82
    zwe
    -0.81
     acoged
    -0.81
    POSITIVE LOGITS
     said
    6.47
    said
    3.41
    Said
    3.19
     Said
    3.17
     gesagt
    2.56
     कहा
    2.34
     сказа
    2.28
     SAID
    2.27
     say
    2.27
     detto
    2.17
    Activations Density 0.032%

    No Known Activations