© 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. 10-GEMMASCOPE-RES-131K
    7. 120001
    Prev
    Next
    INDEX
    Explanations

    common phrases and code structures

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

    commas that appear after the number 0 in code contexts, particularly in range functions and coordinate specifications.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    when
    -2.03
    M
    -2.02
    because
    -1.99
     to
    -1.98
    </em>
    -1.92
    C
    -1.91
    </td>
    -1.91
    P
    -1.86
    in
    -1.84
    R
    -1.81
    POSITIVE LOGITS
    ޏ
    1.93
     dimanche
    1.88
    踉
    1.86
    ㆆ
    1.84
    ズニー
    1.82
    ㈲
    1.82
     profesora
    1.81
    鼯
    1.79
     meilleurs
    1.78
    銠
    1.74
    Activations Density 0.001%

    No Known Activations