© 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. 52123
    Prev
    Next
    INDEX
    Explanations

    allow at least

    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
     funcionalidad
    0.46
    ç
    0.45
    nin
    0.44
    U
    0.44
     rental
    0.43
     basketball
    0.43
     championship
    0.43
     dodge
    0.43
     monastery
    0.43
     sputter
    0.43
    POSITIVE LOGITS
     pernah
    0.48
     опубликова
    0.44
     rumoured
    0.44
     alguma
    0.43
    觎
    0.43
     overshadowed
    0.42
     Jar
    0.41
     Aph
    0.41
    好像
    0.39
     haberse
    0.39
    Activations Density 0.009%

    No Known Activations