© 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. 15873
    Prev
    Next
    INDEX
    Explanations

    data structure initialization

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

    The neuron flags programming‐language tokens—identifiers, keywords, punctuation, and other syntax elements in code snippets.

    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
     now
    -1.13
    кнул
    -1.00
     with
    -0.98
     areas
    -0.95
     activities
    -0.94
    Lưu
    -0.89
     materials
    -0.88
    컴
    -0.88
    gı
    -0.86
     details
    -0.86
    POSITIVE LOGITS
     []*
    0.97
    ㄉ
    0.94
     chiama
    0.94
     semblable
    0.94
    formed
    0.93
     homogeneous
    0.91
    kin
    0.91
    ⑭
    0.91
    referred
    0.91
    专题
    0.91
    Activations Density 0.004%

    No Known Activations