© 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-16K
    7. 1562
    Prev
    Next
    INDEX
    Explanations

    sensual seductive descriptive words

    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_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
    🔎
    0.94
    🖥
    0.94
    📅
    0.92
    📑
    0.91
    📙
    0.91
    👮
    0.88
    ❗
    0.88
    ⏺
    0.87
     discussed
    0.87
    📃
    0.84
    POSITIVE LOGITS
     glistening
    1.19
     iridescent
    1.19
     shimmering
    1.18
     glittering
    1.08
     suave
    1.07
     glitter
    1.06
     hues
    1.04
     deliciously
    1.03
     delectable
    1.03
     otherworldly
    1.01
    Activations Density 0.437%

    No Known Activations