© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 27308
    Prev
    Next
    INDEX
    Explanations

    handle large files or longer contexts

    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_31_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
    7
    0.46
    Provider
    0.43
    Media
    0.42
    ifo
    0.41
    д
    0.40
     Media
    0.40
    Worker
    0.40
    apter
    0.38
    สัญญา
    0.38
     vaccine
    0.38
    POSITIVE LOGITS
     андроид
    0.49
     unequivocally
    0.46
     contemporaries
    0.45
    symmetry
    0.45
     gráf
    0.45
     ದಾಖ
    0.44
    쉘
    0.44
    ப்ச
    0.43
     fraudsters
    0.43
     peculiarly
    0.42
    Activations Density 0.000%

    No Known Activations