© 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. 42172
    Prev
    Next
    INDEX
    Explanations

    buying guide

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

    instructionsavoidingnotbasedgitinvestigationtoolsshouldηtagsbe

    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
     বিষ্ণ
    0.48
    umptions
    0.47
    uccino
    0.46
    uments
    0.46
     Lions
    0.45
    ressant
    0.45
    牵
    0.44
     Фонбет
    0.44
     लिप
    0.43
     Хоккей
    0.42
    POSITIVE LOGITS
     respuesta
    0.46
    し
    0.45
    ပ
    0.45
    Í
    0.43
     പ്രവർ
    0.42
    レストラン
    0.41
    UTF
    0.40
    Ay
    0.40
     prípade
    0.40
     hodnot
    0.40
    Activations Density 0.000%

    No Known Activations