© 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-16K
    7. 3339
    Prev
    Next
    INDEX
    Explanations

    translatable phrases and sentences

    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_16k_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
    vis
    0.46
     di
    0.45
    /
    0.45
    us
    0.45
     ri
    0.45
     intern
    0.45
    u
    0.44
    es
    0.44
     aux
    0.44
    and
    0.44
    POSITIVE LOGITS
    Difficulty
    0.50
    Because
    0.50
     bahawa
    0.50
     что
    0.49
    Bew
    0.49
    Saw
    0.49
    Chronic
    0.48
    敺
    0.48
    璿
    0.48
    DueDate
    0.48
    Activations Density 0.013%

    No Known Activations