© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 107507
    Prev
    Next
    INDEX
    Explanations

    places and things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    president
    0.58
     leurs
    0.55
     luật
    0.52
     nowy
    0.51
     odpowiedzi
    0.49
    }$
    0.49
     pię
    0.49
     mistress
    0.49
    nc
    0.49
     reject
    0.48
    POSITIVE LOGITS
    踽
    0.62
    ༦
    0.60
     но
    0.56
    গুলোতে
    0.56
    的存在
    0.56
     с
    0.54
     ist
    0.54
    ном
    0.54
    狨
    0.54
     го
    0.54
    Activations Density 0.026%

    No Known Activations