© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3626
    Prev
    Next
    INDEX
    Explanations

    candidate verification and ethics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     misschien
    1.19
    这篇文章
    1.19
    它
    1.18
     län
    1.13
     reckons
    1.07
     hulle
    1.05
     here
    1.01
     vă
    1.01
    禍
    1.00
     something
    0.99
    POSITIVE LOGITS
    rinsic
    2.86
     ancillary
    2.85
     numeric
    2.84
     pristine
    2.82
     disparate
    2.80
     harmonious
    2.80
    7
    2.80
     raw
    2.79
     incoming
    2.78
     freestanding
    2.75
    Activations Density 0.185%

    No Known Activations