© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92050
    Prev
    Next
    INDEX
    Explanations

    submit, Submitted, submission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    i
    -1.26
     greateſt
    -1.19
    в
    -1.13
    й
    -1.10
    ex
    -1.09
    읖
    -1.08
    出一个
    -1.05
    在你
    -1.05
    2
    -1.02
    Terrible
    -1.01
    POSITIVE LOGITS
     to
    1.65
    ܜ
    1.62
    tals
    1.52
    彣
    1.43
    鏐
    1.39
    蟊
    1.32
     Submission
    1.30
     onSubmit
    1.23
    那时
    1.22
     canzone
    1.20
    Activations Density 0.025%

    No Known Activations