© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 88941
    Prev
    Next
    INDEX
    Explanations

    bolded terms followed by colon

    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
    Not in Any Lists

    No Comments

    Negative Logits
    punten
    0.64
     î
    0.63
     empêcher
    0.63
     различ
    0.61
     juiste
    0.60
     bepaalde
    0.59
     дево
    0.59
    vred
    0.58
    🩸
    0.58
     деву
    0.57
    POSITIVE LOGITS
     was
    0.69
     is
    0.65
     T
    0.57
     O
    0.57
     K
    0.56
     U
    0.55
     Memory
    0.55
     were
    0.54
    ذ
    0.54
    추
    0.54
    Activations Density 0.652%

    No Known Activations