© 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. 44019
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    USB, fatigue, chorioamnionitis, dosages, joints

    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
     başlang
    0.47
    mobile
    0.45
     specijal
    0.45
     ګرځنده
    0.45
     bellissimo
    0.45
     त्यानंतर
    0.44
    䡃
    0.43
     kemudian
    0.43
    禁止
    0.42
    aktif
    0.42
    POSITIVE LOGITS
    O
    0.57
     upregulation
    0.56
    潞
    0.48
    Effect
    0.48
    झ
    0.47
    Threat
    0.47
    зни
    0.46
    Ideas
    0.46
     TCU
    0.46
     सड़क
    0.46
    Activations Density 0.000%

    No Known Activations