© 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. 60374
    Prev
    Next
    INDEX
    Explanations

    first word or input

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

    This neuron strongly responds to tokens that name variables or parameters (e.g. “start,” “inputs,” “a,” “first,” “input”) in code or math contexts.

    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
     and
    -1.27
     Deze
    -1.06
    ないし
    -1.03
     dostępne
    -1.02
    stand
    -1.02
     dowol
    -1.02
    summer
    -1.01
    ce
    -1.01
    )^{\
    -1.00
     Saints
    -1.00
    POSITIVE LOGITS
     incluyendo
    1.29
     always
    1.27
     it
    1.26
     incluindo
    1.19
     estaba
    1.06
     includ
    1.02
     estava
    1.01
     だけ
    1.00
     admittedly
    1.00
     somehow
    0.99
    Activations Density 0.055%

    No Known Activations