© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 214210
    Prev
    Next
    INDEX
    Explanations

    interpreting sensory inputs

    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_40_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
    ფილი
    0.47
     관계로
    0.42
     다시
    0.41
    sType
    0.38
    vers
    0.37
     हिस्सों
    0.37
     దాని
    0.37
    ⿳
    0.37
    祉
    0.37
     আবারও
    0.36
    POSITIVE LOGITS
     seeking
    0.41
     volunteered
    0.39
     स्ट्रीम
    0.39
     लाइफ
    0.38
     Mehndi
    0.37
     wanting
    0.37
    لاج
    0.37
     divisors
    0.37
    Life
    0.37
     accountant
    0.36
    Activations Density 0.000%

    No Known Activations