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

    Neuronpedia

    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. 49740
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts

    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
     proguard
    0.48
     soạn
    0.44
     sha
    0.43
     chr
    0.43
     theorems
    0.42
     phospholip
    0.41
    簑
    0.41
     mac
    0.41
     codes
    0.40
     map
    0.40
    POSITIVE LOGITS
    ن
    0.51
     Ecology
    0.47
    ec
    0.46
    distributed
    0.46
    ab
    0.46
    training
    0.45
    genesis
    0.45
     Khab
    0.45
    others
    0.44
    ess
    0.44
    Activations Density 0.001%

    No Known Activations