© 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. 31-GEMMASCOPE-2-RES-65K
    7. 12643
    Prev
    Next
    INDEX
    Explanations

    internal or lightning

    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_31_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
    <0x94>
    0.51
    Monthly
    0.50
    Partial
    0.46
    x
    0.45
    Origen
    0.44
    Expiry
    0.43
    Bush
    0.43
    Break
    0.42
    Weekly
    0.42
    Round
    0.42
    POSITIVE LOGITS
     lenses
    0.50
    <unused41>
    0.50
     integrations
    0.48
     YOU
    0.47
     Những
    0.47
     unfairly
    0.47
     Может
    0.45
     tying
    0.45
     SUVs
    0.45
     solidify
    0.44
    Activations Density 0.003%

    No Known Activations