© 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. 223075
    Prev
    Next
    INDEX
    Explanations

    describing risks, media, and inventory

    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
     salvage
    0.43
     pious
    0.41
    ቁ
    0.38
     চালু
    0.38
    िप्ट
    0.38
    ່ວນ
    0.37
     pomoc
    0.37
     salv
    0.36
     graders
    0.36
    }|^{
    0.36
    POSITIVE LOGITS
    好处
    0.42
     Jewelry
    0.41
    üedad
    0.40
    ization
    0.39
    izing
    0.39
     Portrait
    0.39
     Paradox
    0.39
     Description
    0.38
    Description
    0.38
    ologie
    0.37
    Activations Density 0.000%

    No Known Activations