© 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-262K
    7. 28044
    Prev
    Next
    INDEX
    Explanations

    document-related contexts

    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_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
    )}+
    0.41
    ningar
    0.41
    Desc
    0.39
     झाल्यावर
    0.38
    แต่
    0.38
     सेकंड
    0.37
    া
    0.37
    lk
    0.36
     संग
    0.36
    ={
    0.35
    POSITIVE LOGITS
     ataupun
    0.46
     transpar
    0.44
     meandering
    0.43
     angling
    0.41
     Our
    0.41
     Amplifier
    0.41
     incarcer
    0.41
     entitlement
    0.41
     Franck
    0.41
     arbeit
    0.40
    Activations Density 0.000%

    No Known Activations