© 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. 104561
    Prev
    Next
    INDEX
    Explanations

    code manager classes

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

    the word "Manager" in programming code, especially in class names and variable declarations.

    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
    a
    -2.75
    这里
    -2.58
    section
    -2.36
    癰
    -2.28
     utilizzato
    -2.19
    䨻
    -2.19
     aggiunge
    -2.11
     undermine
    -2.11
     vantaggio
    -2.09
     当
    -2.08
    POSITIVE LOGITS
    .
    2.89
    </h3>
    2.72
    </sub>
    2.59
    鲽
    2.39
    <td>
    2.38
     is
    2.30
    相当于
    2.25
    ᠁
    2.23
    ᯾
    2.23
    ܞ
    2.22
    Activations Density 0.008%

    No Known Activations