© 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. 40-GEMMASCOPE-2-RES-262K
    7. 7892
    Prev
    Next
    INDEX
    Explanations

    One followed by explanation

    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_40_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
    Single
    0.25
    και
    0.24
    جار
    0.23
    SINGLE
    0.23
     單
    0.23
    Section
    0.22
    لوار
    0.22
    ####
    0.22
     Single
    0.22
     грошы
    0.22
    POSITIVE LOGITS
     важных
    0.32
    ida
    0.28
     stormy
    0.28
     intriguing
    0.28
     façon
    0.27
    çok
    0.27
     way
    0.27
     fascinating
    0.27
    жды
    0.27
     notable
    0.26
    Activations Density 0.008%

    No Known Activations