© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 3940
    Prev
    Next
    INDEX
    Explanations

    verbs followed by prepositions or 'to'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
    ቀ
    0.93
     garder
    0.90
    yal
    0.88
     オレンジ
    0.88
     nodig
    0.85
     overlooked
    0.83
     確認
    0.82
    checkout
    0.81
     සැල
    0.81
    യോഗ
    0.80
    POSITIVE LOGITS
     shells
    0.64
    iesis
    0.63
     berse
    0.61
    与
    0.60
    材
    0.59
    域
    0.58
     असता
    0.58
    厦
    0.57
    ние
    0.57
    adamia
    0.57
    Activations Density 0.149%

    No Known Activations