© 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. 42038
    Prev
    Next
    INDEX
    Explanations

    outputs, spits, rains, excreted

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     naše
    -1.92
    raeli
    -1.75
    袿
    -1.67
    琑
    -1.66
    pergillus
    -1.64
    (/^
    -1.63
    mazan
    -1.59
     tredje
    -1.58
    姽
    -1.56
    ᐕ
    -1.56
    POSITIVE LOGITS
    )
    2.11
     a
    2.06
     about
    1.90
     Such
    1.78
    '
    1.75
    ,"
    1.74
     "
    1.66
     dicono
    1.63
    <td>
    1.58
     produrre
    1.58
    Activations Density 0.046%

    No Known Activations