© 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. 22-GEMMASCOPE-RES-131K
    7. 66948
    Prev
    Next
    INDEX
    Explanations

    PHP code, specific terms

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

    The neuron responds to structural and formatting tokens—things like section numbers, headers, punctuation marks, and similar layout cues.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     at
    -1.36
     even
    -1.23
     now
    -1.21
    𝒙
    -1.10
     in
    -1.08
     from
    -1.02
     specially
    -1.02
    $\%
    -1.01
     przecież
    -1.00
     plunged
    -0.99
    POSITIVE LOGITS
    rophi
    1.27
    schrift
    1.22
    ofing
    1.16
    queness
    1.15
     Kontak
    1.14
    mpton
    1.12
    unków
    1.12
    antium
    1.12
    struk
    1.10
    tellar
    1.10
    Activations Density 0.001%

    No Known Activations