Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 8229
    Prev
    Next
    INDEX
    Explanations

    and followed by nouns

    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_53_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
    就像
    0.43
     tercero
    0.37
     "):
    0.37
     átomos
    0.37
    ంచరీలు
    0.36
    vocals
    0.36
     relâche
    0.35
    取得了
    0.35
    "?
    0.35
     {}".
    0.35
    POSITIVE LOGITS
     triglyceride
    0.43
    visory
    0.38
     inflationary
    0.37
     വിദ്യാഭ്യാസ
    0.36
     supremacist
    0.35
     ხოლო
    0.35
     egyéb
    0.35
    )・
    0.35
     calorimetric
    0.35
     appellate
    0.34
    Activations Density 0.180%

    No Known Activations