© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 63265
    Prev
    Next
    INDEX
    Explanations

    dates, scenarios, or limitations

    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
    эн
    0.41
    符号
    0.40
    ό
    0.40
     нему
    0.39
    бак
    0.39
     intención
    0.39
     Symptoms
    0.38
     -->'
    0.38
     отношение
    0.38
    i
    0.38
    POSITIVE LOGITS
    Specifically
    0.51
     Specifically
    0.48
     לב
    0.46
    ৃষ্ট
    0.45
     لب
    0.45
     Manohar
    0.44
     catamaran
    0.44
     patented
    0.44
     بالاتر
    0.44
    वेज
    0.43
    Activations Density 0.001%

    No Known Activations