© 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-262K
    7. 71502
    Prev
    Next
    INDEX
    Explanations

    prescient, viral, waste, mucus, dye, outputs, quality

    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_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
    ;
    0.44
    Each
    0.43
    দ
    0.43
    `
    0.43
    HDMI
    0.43
    ...
    0.42
    유
    0.42
    鎧
    0.42
    ပ
    0.41
    ଦ
    0.41
    POSITIVE LOGITS
     língua
    0.49
     weib
    0.45
     hype
    0.44
     Lyng
    0.44
     visão
    0.43
     ли
    0.43
     cuerda
    0.43
    ewek
    0.42
    ुल्लाह
    0.42
     sebanyak
    0.42
    Activations Density 0.007%

    No Known Activations