© 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-65K
    7. 12522
    Prev
    Next
    INDEX
    Explanations

    even without

    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_65k_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
    awks
    0.54
    /">
    0.51
    یں۔
    0.48
    ibley
    0.47
    ần
    0.47
    unst
    0.47
    uşt
    0.47
    یکیشن
    0.46
    itel
    0.45
    "]/
    0.45
    POSITIVE LOGITS
     ischemia
    0.46
     damping
    0.46
     isotope
    0.45
     enfer
    0.45
    {
    0.45
     samoglas
    0.44
     discouraging
    0.44
     attenuation
    0.44
     outbreaks
    0.43
     eradic
    0.43
    Activations Density 0.005%

    No Known Activations