© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 5037
    Prev
    Next
    INDEX
    Explanations

    encourages efficient process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     v
    0.75
     ви
    0.73
    Media
    0.73
    шей
    0.72
    v
    0.72
    wit
    0.72
    SKI
    0.70
     ws
    0.69
     ш
    0.69
    Ди
    0.67
    POSITIVE LOGITS
     encourages
    1.01
     acceptability
    1.00
     efficient
    0.99
     prevents
    0.94
     immunost
    0.93
     profitable
    0.93
     pleasing
    0.92
     helps
    0.91
     prohibits
    0.91
     maximizes
    0.90
    Activations Density 0.000%

    No Known Activations