© 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-16K
    7. 3544
    Prev
    Next
    INDEX
    Explanations

    creative and design qualities

    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_16k_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
    美国
    0.46
     Putin
    0.45
     homosexuality
    0.45
    税
    0.44
    一下
    0.44
     the
    0.43
     Mussolini
    0.42
     certain
    0.42
    하면
    0.41
    蛄
    0.41
    POSITIVE LOGITS
     ingenious
    0.56
     sleek
    0.48
     idées
    0.48
     hochwertige
    0.48
     attrakt
    0.47
     vielfält
    0.47
    创意
    0.46
     আকর্ষণীয়
    0.46
     catchy
    0.46
     innovative
    0.45
    Activations Density 0.245%

    No Known Activations