© 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. 10-GEMMASCOPE-RES-131K
    7. 113818
    Prev
    Next
    INDEX
    Explanations

    HTML tags or code comments

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

    opening angle brackets in HTML/XML markup tags.

    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
    2
    -3.58
    5
    -2.91
    1
    -2.80
    6
    -2.69
    7
    -2.52
    ><
    -2.45
    \
    -2.42
    3
    -2.36
    <td>
    -2.28
    It
    -2.13
    POSITIVE LOGITS
    犼
    2.19
     allerlei
    2.11
     入っ
    2.03
    لوار
    1.98
    烀
    1.97
    餮
    1.94
     they
    1.93
    攆
    1.92
    ープン
    1.91
    衚
    1.90
    Activations Density 0.000%

    No Known Activations