© 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. 22-GEMMASCOPE-RES-131K
    7. 73519
    Prev
    Next
    INDEX
    Explanations

    following punctuation

    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_22/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
    ㅐ
    -1.04
    颚
    -1.02
     интерьере
    -1.02
     gemeenten
    -1.00
    </u>
    -1.00
    });
    -0.99
     particular
    -0.99
     indisputable
    -0.98
     непосредственно
    -0.96
    ₜ
    -0.96
    POSITIVE LOGITS
     that
    1.20
    もあって
    1.18
    ～！
    1.16
     cintura
    1.15
    اعده
    1.14
    gingen
    1.14
    婞
    1.12
     silueta
    1.11
     totalité
    1.10
    日は
    1.09
    Activations Density 0.002%

    No Known Activations