© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 1940
    Prev
    Next
    INDEX
    Explanations

    Russian characters and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     égard
    0.52
    😿
    0.51
     стаўкі
    0.51
     možda
    0.46
     Fallon
    0.45
     えっ
    0.45
     فونیټ
    0.45
     る
    0.44
     ImageIcon
    0.44
     सॉरी
    0.44
    POSITIVE LOGITS
    Д
    0.81
    С
    0.79
    За
    0.77
    Ро
    0.75
    При
    0.75
    Об
    0.75
    Р
    0.75
    У
    0.75
    В
    0.74
    На
    0.74
    Activations Density 0.000%

    No Known Activations