© 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. 224226
    Prev
    Next
    INDEX
    Explanations

    multiple languages and administration

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

    abstraction, pattern

    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
     tombs
    0.53
     cristiana
    0.51
    wiches
    0.49
    avg
    0.47
    °;
    0.46
     flank
    0.46
     Yan
    0.46
     urch
    0.46
     muros
    0.46
    ĝ
    0.46
    POSITIVE LOGITS
    шого
    0.45
     первых
    0.43
    力的
    0.42
    ័
    0.41
     начальник
    0.40
     directeur
    0.39
    日の
    0.39
    秫
    0.39
    르면
    0.39
    Compressed
    0.39
    Activations Density 0.001%

    No Known Activations