© 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. 30004
    Prev
    Next
    INDEX
    Explanations

    design and planning

    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
     on
    0.69
     is
    0.69
     path
    0.69
    ).
    0.68
     driveway
    0.68
     play
    0.67
     pathway
    0.67
    )
    0.66
     translation
    0.66
     compress
    0.66
    POSITIVE LOGITS
    Design
    1.05
    Designing
    0.98
    it
    0.98
     Designs
    0.98
    Designs
    0.93
    in
    0.91
    ir
    0.91
     Diseño
    0.91
     Design
    0.90
    ar
    0.89
    Activations Density 0.068%

    No Known Activations