© 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. 10141
    Prev
    Next
    INDEX
    Explanations

    becomes attracted and then starts

    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
    ల్‌
    0.42
    かもしれません
    0.39
    書
    0.37
    如果你
    0.37
    你可以
    0.37
    ):
    0.36
    ():
    0.35
    াঃ
    0.35
    ：“
    0.35
     אם
    0.34
    POSITIVE LOGITS
     undead
    0.40
     hedon
    0.38
     chiral
    0.37
     parten
    0.36
     promove
    0.36
     logra
    0.35
     kund
    0.35
     propos
    0.34
     Kund
    0.33
     captivity
    0.33
    Activations Density 0.329%

    No Known Activations