© 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. 210188
    Prev
    Next
    INDEX
    Explanations

    emotional and technical descriptions

    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
    drinking
    0.38
    violence
    0.37
    ▴
    0.37
    smoothing
    0.37
    IVERSITY
    0.37
    スティ
    0.37
    गांव
    0.37
     gravitate
    0.37
     aliphatic
    0.36
     ellipsoid
    0.36
    POSITIVE LOGITS
     ক
    0.45
     וח
    0.42
     disguise
    0.41
     unaware
    0.39
     वस्त्र
    0.38
     uns
    0.37
     അവരുടെ
    0.37
    橱
    0.37
    櫥
    0.37
     floor
    0.36
    Activations Density 0.000%

    No Known Activations