© 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. 108620
    Prev
    Next
    INDEX
    Explanations

    bullet points and lists

    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
     {
    0.47
    ja
    0.44
    ..--..--
    0.44
     Mpc
    0.44
     quartzite
    0.43
     leftist
    0.42
     CAUSED
    0.42
     Papua
    0.42
    nota
    0.42
     inaccuracies
    0.42
    POSITIVE LOGITS
    環境
    0.46
    فير
    0.45
    に必要な
    0.43
    前
    0.42
     учё
    0.39
    -
    0.39
    㳑
    0.38
     አመ
    0.38
     इस्तेमाल
    0.38
    放
    0.38
    Activations Density 0.002%

    No Known Activations