© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 3704
    Prev
    Next
    INDEX
    Explanations

    legal prepositions thereof herein therein wherein

    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
    Everything
    1.08
     nevoie
    0.95
     אנחנו
    0.92
     everything
    0.89
     огром
    0.88
     Everything
    0.87
    <unused2131>
    0.87
     정말
    0.86
    ார்கள்
    0.86
     EVERYTHING
    0.86
    POSITIVE LOGITS
     thereof
    2.19
     therefrom
    1.90
     thereto
    1.89
     plurality
    1.87
     thereon
    1.80
     therewith
    1.75
    wherein
    1.72
     therein
    1.66
     wherein
    1.66
     aforesaid
    1.58
    Activations Density 0.070%

    No Known Activations