© 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. 29-GEMMASCOPE-2-RES-16K
    7. 2787
    Prev
    Next
    INDEX
    Explanations

    words ending in ant, ancy, ent

    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
    かし
    0.73
    ىلى
    0.69
    વાડી
    0.68
    淼
    0.67
    ုပ်
    0.66
    肌
    0.65
     लिव
    0.65
    㖑
    0.65
     ちゃ
    0.65
    ﺡ
    0.64
    POSITIVE LOGITS
    ANT
    2.58
    ant
    2.57
    ants
    2.54
    Ant
    2.43
     Ant
    2.27
     ant
    2.25
    ents
    2.22
     ANT
    2.18
    ent
    2.16
    antes
    2.13
    Activations Density 0.695%

    No Known Activations