© 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-65K
    7. 40208
    Prev
    Next
    INDEX
    Explanations

    cheapest flights

    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_65k_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
    ্যাগ
    0.45
    减
    0.44
    чём
    0.43
    ச்சின்ன
    0.43
    Emojis
    0.43
    惊
    0.42
    FromNib
    0.41
     αυτο
    0.40
     być
    0.39
    滩
    0.39
    POSITIVE LOGITS
     lejos
    0.41
     niti
    0.41
    ulnerable
    0.40
     considerable
    0.39
     capabilities
    0.38
    ласти
    0.38
     heft
    0.37
    jectories
    0.37
     substantial
    0.37
     curses
    0.37
    Activations Density 0.002%

    No Known Activations