© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13519
    Prev
    Next
    INDEX
    Explanations

    latent space, autoencoders, Twitch, passive-aggressive

    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
     пару
    0.44
     alkaloids
    0.44
     miRNAs
    0.43
     phospholipids
    0.43
     ಔಷ
    0.42
    役割
    0.42
     દ
    0.41
     აღმასრულ
    0.41
     ګرځ
    0.41
    新たに
    0.40
    POSITIVE LOGITS
    вшийся
    0.44
     मैने
    0.44
     portable
    0.40
     retouch
    0.38
    Work
    0.38
     sketchbook
    0.38
    峤
    0.38
    portable
    0.37
    ئة
    0.37
    哝
    0.37
    Activations Density 0.042%

    No Known Activations