© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 11593
    Prev
    Next
    INDEX
    Explanations

    observing nature and activities

    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_9_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
    Ironically
    1.14
    ✔
    1.12
    🥇
    1.12
    ଏ
    1.11
    ❌
    1.10
    Еще
    1.10
     payoff
    1.08
    繍
    1.06
     opcion
    1.06
     изготовления
    1.06
    POSITIVE LOGITS
     chats
    1.18
     Kindness
    1.17
     observing
    1.17
     gesturing
    1.17
     solitude
    1.16
     walks
    1.14
     jogging
    1.14
    walking
    1.13
     joggers
    1.13
     Observation
    1.12
    Activations Density 0.141%

    No Known Activations