© 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. 22-GEMMASCOPE-RES-131K
    7. 73175
    Prev
    Next
    INDEX
    Explanations

    Q statements and certificates

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

    The neuron fires on unified‐diff hunk metadata and added‐line markers (the “@@” hunk headers and leading “+” in patch diffs).

    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
     its
    -1.37
     daban
    -1.21
     jobb
    -1.20
    ־
    -1.20
    ༵
    -1.17
    )।
    -1.17
    ৹
    -1.16
     syk
    -1.16
     venner
    -1.14
     Dezember
    -1.13
    POSITIVE LOGITS
     and
    1.55
    Etape
    1.28
    きち
    1.23
     mentre
    1.21
     gekauft
    1.16
    ケモン
    1.14
     whereby
    1.13
     geprüft
    1.13
     sherpa
    1.11
     Enables
    1.11
    Activations Density 0.000%

    No Known Activations