© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203410
    Prev
    Next
    INDEX
    Explanations

    non-english or mixed languages

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

    naval extravagance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constable
    0.52
     strada
    0.51
     cento
    0.49
     delightful
    0.49
     comandante
    0.48
     emerge
    0.47
     inteligente
    0.47
     گ
    0.47
     estadounidense
    0.46
     cunning
    0.45
    POSITIVE LOGITS
    èque
    0.48
    Liens
    0.47
     করিয়াছিলেন
    0.47
    ěstí
    0.46
    เกี่ยวข้อง
    0.44
    níku
    0.43
    으로서
    0.43
     Stry
    0.42
    ptic
    0.42
    ால்
    0.42
    Activations Density 0.001%

    No Known Activations