© 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. 17-GEMMASCOPE-2-RES-16K
    7. 10063
    Prev
    Next
    INDEX
    Explanations

    conversational filler "you know"

    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_17_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
    RELATED
    1.12
     ع
    1.09
    يك
    1.08
     commotion
    1.02
    ঠাৎ
    0.97
    श
    0.95
    ﻴ
    0.92
    पहले
    0.92
     Schwer
    0.91
     Informatics
    0.91
    POSITIVE LOGITS
     parental
    1.15
     contexts
    1.13
     digoxin
    1.10
     vesicles
    1.08
     perfecting
    1.07
     sabb
    1.05
    是多少
    1.05
     avail
    1.04
     lassen
    1.03
    ]}/${
    1.03
    Activations Density 0.006%

    No Known Activations