© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2748
    Prev
    Next
    INDEX
    Explanations

    even if clauses

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    с
    2.24
    it
    1.92
    м
    1.91
     InputStream
    1.76
    otoxicity
    1.76
    특별시
    1.75
    ്ട
    1.68
    ました
    1.64
    로
    1.62
    ка
    1.59
    POSITIVE LOGITS
     несмотря
    2.26
    ことが多い
    2.17
    のは
    2.02
     utterance
    1.97
    Ꮃ
    1.95
     бывшего
    1.94
    ュ
    1.93
     utterances
    1.92
     herramient
    1.92
     pecc
    1.90
    Activations Density 0.111%

    No Known Activations