© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54977
    Prev
    Next
    INDEX
    Explanations

    dead identity, past active

    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
    ၊
    0.55
     Moderators
    0.45
    법
    0.44
    ቆዳ
    0.43
     eğer
    0.43
    খানেই
    0.42
     Infine
    0.42
     Disabled
    0.41
     Pou
    0.41
    占用
    0.41
    POSITIVE LOGITS
     ভর
    0.47
     skyline
    0.46
    wijs
    0.44
    ARR
    0.42
     skepticism
    0.40
    ی
    0.40
     premiere
    0.40
     постро
    0.40
     premiered
    0.40
     vált
    0.40
    Activations Density 0.011%

    No Known Activations