© 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. 25820
    Prev
    Next
    INDEX
    Explanations

    explanation

    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
    Counsel
    0.46
     तीर्थ
    0.45
    ⎮
    0.43
    sgál
    0.43
    rexham
    0.43
     Counseling
    0.42
    isit
    0.42
     repatriation
    0.42
    你們
    0.41
    asena
    0.41
    POSITIVE LOGITS
     because
    0.57
     porque
    0.50
    a
    0.49
     omdat
    0.47
     keyboard
    0.46
    因为
    0.46
    ه
    0.46
     hydrogen
    0.45
     weil
    0.45
    یل
    0.45
    Activations Density 0.006%

    No Known Activations