© 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. 18941
    Prev
    Next
    INDEX
    Explanations

    fading beam

    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
     вони
    0.50
    RECOMM
    0.45
    ุ
    0.45
    They
    0.44
     peasant
    0.44
    ారా
    0.41
    А
    0.41
    ού
    0.40
    водства
    0.40
     clueless
    0.40
    POSITIVE LOGITS
     Dise
    0.43
     cited
    0.42
     Treasure
    0.42
     utilised
    0.41
     Catalogue
    0.40
     Resources
    0.40
     KeyError
    0.38
    rizes
    0.38
     Gorge
    0.38
     Epsom
    0.38
    Activations Density 0.003%

    No Known Activations