© 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. 10-GEMMASCOPE-RES-131K
    7. 112542
    Prev
    Next
    INDEX
    Explanations

    instrumented / autistic

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

    The neuron fires on tokens containing the substring “instr,” i.e. fragments of words like instrumented or instruction.

    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
    m
    -3.23
    </b>
    -2.39
    c
    -2.33
    彀
    -2.31
     &
    -2.14
    ſſi
    -2.13
    ⦊
    -2.08
     \"
    -1.97
    ding
    -1.96
    嚷
    -1.96
    POSITIVE LOGITS
    "
    3.39
    '
    3.08
     ยัง
    2.55
    在
    2.41
    也
    2.39
     cromado
    2.36
    ی
    2.31
    ’
    2.30
    béco
    2.20
    菖
    2.20
    Activations Density 0.008%

    No Known Activations