© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14649
    Prev
    Next
    INDEX
    Explanations

    categories and descriptions

    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
    >*</
    0.45
    Academic
    0.43
     неза
    0.43
    サート
    0.43
     প্রস্তুতি
    0.40
    
    0.38
     момента
    0.38
    
    0.38
    education
    0.38
     ресу
    0.37
    POSITIVE LOGITS
     rearrangements
    0.52
     discussing
    0.46
     denying
    0.44
     చూడ
    0.43
     helps
    0.42
     discussed
    0.42
     determines
    0.41
     determining
    0.40
     details
    0.39
     reimag
    0.39
    Activations Density 0.002%

    No Known Activations