© 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. 250235
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     ප
    0.48
     Nielsen
    0.46
     hurting
    0.44
    jähr
    0.43
     Wür
    0.43
     Niet
    0.42
     ನೇ
    0.42
     Nicholson
    0.42
     Jensen
    0.41
    丑
    0.41
    POSITIVE LOGITS
    overlap
    0.50
    INTS
    0.50
     delights
    0.49
     appreciative
    0.45
    o
    0.45
     excursions
    0.44
     capitals
    0.44
    extrémité
    0.44
    organizations
    0.44
    orthogonal
    0.44
    Activations Density 0.007%

    No Known Activations