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. 31-GEMMASCOPE-2-RES-16K
    4. 12808
    Prev
    Next
    INDEX
    Explanations

    importing code modules

    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
     fluxes
    0.47
    ↵↵
    0.46
    ták
    0.44
    jsx
    0.43
    ([
    0.42
    蒂
    0.42
    kter
    0.42
    ⸨
    0.42
     Já
    0.42
    кера
    0.42
    POSITIVE LOGITS
    ॉग
    0.51
     saada
    0.48
     goTo
    0.47
     dictionary
    0.45
     get
    0.45
     typewriter
    0.45
     isEmpty
    0.45
     cortar
    0.45
     colorChoice
    0.41
    ጠቀም
    0.41
    Activations Density 0.010%

    No Known Activations