© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 49948
    Prev
    Next
    INDEX
    Explanations

    Rust types and associated blocks

    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
     அறிவு
    0.42
    ığım
    0.41
    īng
    0.38
    berger
    0.38
     нормы
    0.38
    Ҡ
    0.38
    􀂃
    0.37
     водой
    0.37
     ağı
    0.36
    𝓇
    0.36
    POSITIVE LOGITS
    덴
    0.40
    DMA
    0.38
     so
    0.38
     lending
    0.38
     Raman
    0.37
    IMG
    0.37
     Derr
    0.37
     confidence
    0.37
     Bao
    0.37
     suture
    0.36
    Activations Density 0.017%

    No Known Activations