© 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. 145
    Prev
    Next
    INDEX
    Explanations

    "logic", "registry", "chicken", "paper", "wage", "crisis", "floor", "cream", "fiber"

    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
     ardent
    0.28
     hjäl
    0.26
     fantastical
    0.26
    魍
    0.26
     subjug
    0.26
     sadistic
    0.26
     هذا
    0.26
     alasan
    0.26
     mischiev
    0.26
     errone
    0.25
    POSITIVE LOGITS
     and
    0.47
    ing
    0.41
    and
    0.39
    7
    0.37
    ok
    0.36
    4
    0.36
    ik
    0.36
    у
    0.34
    ina
    0.34
    ная
    0.33
    Activations Density 0.384%

    No Known Activations