© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 3056
    Prev
    Next
    INDEX
    Explanations

    Here's a breakdown

    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
    +")
    0.28
     Москве
    0.27
    ’).
    0.26
    ’
    0.25
     malaria
    0.25
    闊
    0.25
     adjoint
    0.25
     endowment
    0.24
     bremsstrahlung
    0.23
    genomes
    0.23
    POSITIVE LOGITS
     சுமார்
    0.27
    ore
    0.26
    】
    0.26
    imgur
    0.26
     hozzá
    0.26
    त्या
    0.25
    有一些
    0.25
     तिथि
    0.25
     مؤرشف
    0.25
    ಲ್ಲ
    0.25
    Activations Density 0.066%

    No Known Activations