© 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. 58563
    Prev
    Next
    INDEX
    Explanations

    gulab jamuns, kurdi, qibray names

    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
    皤
    -1.98
     Những
    -1.86
     Есть
    -1.86
     những
    -1.85
     аспек
    -1.83
    谩
    -1.82
    駸
    -1.79
     вось
    -1.76
     incomparable
    -1.75
    鲽
    -1.75
    POSITIVE LOGITS
     It
    2.45
    $
    2.27
    </h5>
    2.20
    }
    2.19
     If
    2.09
    ’
    2.02
     pondering
    1.98
     merav
    1.97
    𝙣
    1.92
    </td>
    1.89
    Activations Density 0.001%

    No Known Activations