© 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. 6171
    Prev
    Next
    INDEX
    Explanations

    micrometers, innervated, at least

    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
     자동으로
    0.41
    बीर
    0.40
    𝓐
    0.39
     Bakın
    0.39
     capturedPlayer
    0.38
     автор
    0.38
     어떻게
    0.38
    EnglishMarks
    0.37
    Კ
    0.37
     клуба
    0.37
    POSITIVE LOGITS
     however
    0.37
     in
    0.36
     used
    0.36
     greatly
    0.36
    have
    0.35
     particularly
    0.35
     have
    0.35
    不過
    0.34
    character
    0.34
    因此
    0.34
    Activations Density 0.358%

    No Known Activations