© 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. 41-GEMMASCOPE-2-RES-262K
    7. 22196
    Prev
    Next
    INDEX
    Explanations

    sweet diversion

    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_all/layer_41_width_262k_l0_big
    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
    रावट
    0.45
    Ō
    0.44
     inodes
    0.43
    鯤
    0.41
     формат
    0.41
     держав
    0.40
     mieux
    0.40
     integrator
    0.40
    indices
    0.39
     тка
    0.39
    POSITIVE LOGITS
     sweet
    0.90
     Sweet
    0.86
    Sweet
    0.81
    甜
    0.80
    sweet
    0.69
     tooth
    0.65
     Sixteen
    0.61
     sweeter
    0.60
     sweetness
    0.55
     ngọt
    0.53
    Activations Density 0.003%

    No Known Activations