© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 87193
    Prev
    Next
    INDEX
    Explanations

    wake word, run, Black, Oscar Piastri, co-branded

    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
     cittam
    0.58
     strides
    0.57
     आवश्यक
    0.54
     crosses
    0.52
    ش
    0.52
     Insect
    0.51
     согла
    0.51
     observance
    0.51
     claves
    0.51
    ěli
    0.50
    POSITIVE LOGITS
    0
    0.59
    bend
    0.53
    Human
    0.52
    _
    0.52
    visited
    0.52
    Client
    0.51
    Season
    0.51
    Est
    0.50
    1
    0.50
    Ak
    0.49
    Activations Density 0.000%

    No Known Activations