© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 115652
    Prev
    Next
    INDEX
    Explanations

    external storage permission

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

    The neuron fires on structural code or configuration tokens—things like “#” directives, XML namespace or permission attribute names, and other programming‐syntax markers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     wired
    -0.71
    міст
    -0.68
    }(),
    -0.63
    nF
    -0.63
    Programme
    -0.63
    ımız
    -0.62
     neutro
    -0.62
    wired
    -0.62
     Oneida
    -0.60
    爪
    -0.60
    POSITIVE LOGITS
    レーン
    0.75
    recovery
    0.73
    Т
    0.67
     hires
    0.66
    Recovery
    0.66
    собенно
    0.65
     RECOVERY
    0.65
    ան
    0.64
    зий
    0.63
    MT
    0.63
    Activations Density 0.083%

    No Known Activations