© 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-65K
    7. 3817
    Prev
    Next
    INDEX
    Explanations

    mermaid diagram syntax

    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_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
     contratto
    0.40
     columnas
    0.40
    綎
    0.40
    点は
    0.39
     auspices
    0.39
     respald
    0.39
    転
    0.38
    itum
    0.38
     convective
    0.38
     bedeut
    0.38
    POSITIVE LOGITS
    सारा
    0.39
     Agric
    0.37
    威尔
    0.37
    wheel
    0.37
    ף
    0.36
     Planned
    0.36
     Shill
    0.36
    rizona
    0.36
     Keb
    0.36
     முழுவதும்
    0.35
    Activations Density 0.020%

    No Known Activations