© 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. 35319
    Prev
    Next
    INDEX
    Explanations

    discuss your needs

    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
    z
    0.55
    ues
    0.54
     prise
    0.51
    able
    0.50
     pensions
    0.50
    el
    0.50
     Floor
    0.49
    populations
    0.49
     Decade
    0.49
    erosion
    0.49
    POSITIVE LOGITS
     değişiklik
    0.53
     applicazioni
    0.49
     }}$.
    0.48
     zada
    0.48
     descargar
    0.47
     disponibil
    0.47
    $/.
    0.46
     pentru
    0.46
     ooz
    0.46
     desple
    0.46
    Activations Density 0.000%

    No Known Activations