© 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. 40-GEMMASCOPE-2-RES-262K
    7. 84922
    Prev
    Next
    INDEX
    Explanations

    sentience and sentimental

    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
    麪
    0.41
    μία
    0.41
    édon
    0.39
     ھ
    0.39
    ITCH
    0.39
    SCOPE
    0.38
     স্কোর
    0.38
     Commitment
    0.37
    َہ
    0.37
    Scope
    0.37
    POSITIVE LOGITS
    tering
    0.47
    icent
    0.47
    cent
    0.47
    idescent
    0.45
     pent
    0.44
    imental
    0.44
     sentir
    0.42
     sentiments
    0.42
     sientes
    0.42
    isent
    0.41
    Activations Density 0.014%

    No Known Activations