© 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. 9-GEMMASCOPE-2-RES-262K
    7. 10503
    Prev
    Next
    INDEX
    Explanations

    describing past events and states

    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
    యే
    1.19
    𝘿
    1.19
    nullable
    1.17
    िक
    1.16
     repl
    1.11
    naments
    1.08
    rugged
    1.07
     slender
    1.07
    Contributor
    1.06
    Diss
    1.05
    POSITIVE LOGITS
    e
    1.51
    ে
    1.29
     dispensers
    1.26
    段
    1.24
     차
    1.24
    螂
    1.18
    ل
    1.17
     butchers
    1.16
     zeuden
    1.15
    NSE
    1.14
    Activations Density 0.000%

    No Known Activations