© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 8837
    Prev
    Next
    INDEX
    Explanations

    adverbs preceding negative or intense descriptions

    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
    the
    1.39
    1
    1.21
    The
    1.18
    0
    1.16
    what
    1.15
    2
    1.14
    6
    1.09
    3
    1.09
     to
    1.08
     a
    1.07
    POSITIVE LOGITS
     arduous
    1.18
    oramic
    1.17
     hefty
    1.12
    ocious
    1.09
     resolute
    1.06
     unrelenting
    1.05
     conco
    1.05
    ländischen
    1.03
     perilous
    1.01
     $*$-
    1.00
    Activations Density 0.615%

    No Known Activations