© 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. 10-GEMMASCOPE-RES-131K
    7. 60132
    Prev
    Next
    INDEX
    Explanations

    wood types and products

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

    The neuron detects mentions of wood materials or specific wood types (e.g. “wood,” “maple,” “veneer,” “hardwood”).

    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
     verze
    -1.40
    žiaga
    -1.34
    raten
    -1.25
    arem
    -1.21
    tmp
    -1.20
    tp
    -1.19
     verhind
    -1.16
     constate
    -1.16
     Stiftung
    -1.15
     plát
    -1.15
    POSITIVE LOGITS
     some
    1.46
    </h3>
    1.31
     how
    1.26
     then
    1.21
     wood
    1.19
     our
    1.17
     that
    1.14
     proveniente
    1.08
     does
    1.05
     what
    1.04
    Activations Density 0.063%

    No Known Activations