© 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. 27108
    Prev
    Next
    INDEX
    Explanations

    re recipe Personnel complications functionality

    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
    lyPlugin
    0.51
     consonant
    0.44
    脾
    0.43
    јан
    0.42
    лика
    0.42
     আকৃষ্ট
    0.42
    俅
    0.42
     kilowatt
    0.41
     lignin
    0.40
    шок
    0.40
    POSITIVE LOGITS
     Everywhere
    0.45
    re
    0.43
     Marg
    0.42
     B
    0.42
     Grav
    0.42
    Multi
    0.41
     Simultaneous
    0.41
     Therapeutics
    0.41
    INTERVAL
    0.40
    SA
    0.40
    Activations Density 0.015%

    No Known Activations