© 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. 31-GEMMASCOPE-2-RES-262K
    7. 32241
    Prev
    Next
    INDEX
    Explanations

    you see or join

    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_31_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
    毆
    0.52
     indicadores
    0.50
     telefon
    0.49
     klub
    0.49
     leaks
    0.48
     impulso
    0.48
    نوات
    0.48
     exigences
    0.47
     demandas
    0.47
     ofertas
    0.46
    POSITIVE LOGITS
    rt
    0.59
    r
    0.56
    v
    0.56
    l
    0.55
    ds
    0.54
    asını
    0.52
    ret
    0.51
    theta
    0.50
    or
    0.50
    lc
    0.50
    Activations Density 0.001%

    No Known Activations