© 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-16K
    7. 11914
    Prev
    Next
    INDEX
    Explanations

    phrases starting with specific tokens

    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_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
     ultraviolet
    0.45
    <unused2179>
    0.45
    ヾ
    0.45
    lwjglVersion
    0.44
     অর্থাৎ
    0.43
    〠
    0.43
     यानी
    0.43
    এবং
    0.42
     detoxification
    0.42
    ;
    0.41
    POSITIVE LOGITS
     mags
    0.50
     avis
    0.47
     antics
    0.45
     NGOs
    0.44
     presos
    0.44
     regs
    0.43
     shenanigans
    0.43
    議論
    0.43
     Baron
    0.41
     सामान
    0.40
    Activations Density 0.148%

    No Known Activations