© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 148159
    Prev
    Next
    INDEX
    Explanations

    creating, describing, specifying

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_262k_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
     seluruh
    0.85
     keduanya
    0.75
    ᱑
    0.73
    completely
    0.70
    adle
    0.70
     semua
    0.69
     leaked
    0.69
     deleteAll
    0.68
     deberían
    0.67
    ()):
    0.67
    POSITIVE LOGITS
     adding
    1.12
     designating
    1.09
     enhancing
    1.08
     specifying
    1.04
     Adding
    1.03
     simulating
    0.97
     describing
    0.96
     depicting
    0.93
     telling
    0.93
     choosing
    0.90
    Activations Density 0.001%

    No Known Activations