© 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. 40-GEMMASCOPE-2-RES-262K
    7. 195279
    Prev
    Next
    INDEX
    Explanations

    JavaScript execution context

    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_262k_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
    貌
    0.41
    insel
    0.38
    PACK
    0.37
    setImage
    0.36
     FITNESS
    0.36
     दमखम
    0.36
    DBOutput
    0.36
    面
    0.36
    IGNORE
    0.35
     SH
    0.35
    POSITIVE LOGITS
     gathering
    0.40
     kar
    0.38
     translating
    0.38
    तुम
    0.38
    eking
    0.37
    ivere
    0.37
     kro
    0.37
    தன்
    0.37
     renting
    0.36
    ducible
    0.36
    Activations Density 0.000%

    No Known Activations