© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 45498
    Prev
    Next
    INDEX
    Explanations

    hummingbird

    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
     algumas
    0.54
     botón
    0.54
     όταν
    0.52
     femininity
    0.52
     elevado
    0.51
     cytokinin
    0.51
     waveform
    0.50
    બ
    0.50
     suspending
    0.49
     botones
    0.49
    POSITIVE LOGITS
    l
    0.86
    r
    0.84
    n
    0.80
    R
    0.71
    tal
    0.70
    to
    0.70
    чка
    0.68
    er
    0.68
    t
    0.68
    their
    0.68
    Activations Density 0.001%

    No Known Activations