© 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. 28485
    Prev
    Next
    INDEX
    Explanations

    * or numbered list items

    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
     doy
    0.41
    baum
    0.40
     Purple
    0.40
     atu
    0.39
     -
    0.39
     oe
    0.39
    </i>
    0.38
     MDF
    0.38
     Charlie
    0.38
    ributed
    0.38
    POSITIVE LOGITS
    <unused82>
    0.41
    CCOCC
    0.41
    áš
    0.39
     `<=`
    0.39
    ']->
    0.38
    трон
    0.38
     كثير
    0.36
    étés
    0.35
     prisión
    0.35
     பொறிய
    0.35
    Activations Density 0.024%

    No Known Activations