© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62767
    Prev
    Next
    INDEX
    Explanations

    Raptor, METHOD, support, 1, Month, “

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

    The neuron fires on named entities and technical identifiers—proper nouns (e.g. game titles or person names) and code‐level tokens like class/method/field names.

    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
     radically
    -0.83
    __(/*!
    -0.77
     as
    -0.74
     enhancing
    -0.73
     Momo
    -0.72
     !!
    -0.72
     F
    -0.71
    嫻
    -0.70
     E
    -0.69
    úi
    -0.69
    POSITIVE LOGITS
     Vuitton
    0.94
    rune
    0.82
    uelan
    0.81
     RSI
    0.81
    Isaac
    0.80
     aguard
    0.80
    agge
    0.79
    atric
    0.79
    kuš
    0.79
    perhaps
    0.77
    Activations Density 0.004%

    No Known Activations