© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111693
    Prev
    Next
    INDEX
    Explanations

    commands and code snippets

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

    line breaks or newlines that separate list items, code blocks, or structured content entries.

    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
    ization
    -2.14
    ies
    -1.85
    izing
    -1.82
    il
    -1.79
     norvég
    -1.76
    is
    -1.61
    ताओं
    -1.61
     betyd
    -1.59
     membersihkan
    -1.59
    𝑧
    -1.59
    POSITIVE LOGITS
    </em>
    2.08
    ጺ
    1.72
     velha
    1.71
     honest
    1.61
     braço
    1.60
    <
    1.59
    彞
    1.59
     dessa
    1.59
    Their
    1.56
    </td>
    1.55
    Activations Density 0.295%

    No Known Activations