© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 16270
    Prev
    Next
    INDEX
    Explanations

    distinguishing superficial from core

    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
    юще
    0.42
    masının
    0.41
     radiations
    0.41
    ۔
    0.41
    ùm
    0.41
    jectives
    0.40
     многочис
    0.40
     مقامی
    0.39
     குடியிருப்ப
    0.39
    ầm
    0.39
    POSITIVE LOGITS
    ，
    0.50
     anbef
    0.48
     porad
    0.46
     ，
    0.46
     to
    0.45
    或
    0.45
     improve
    0.43
     camel
    0.43
     sio
    0.43
     enhance
    0.43
    Activations Density 0.002%

    No Known Activations