© 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. 54819
    Prev
    Next
    INDEX
    Explanations

    SQL create table statements

    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
    >`,
    0.36
    ble
    0.35
    >{
    0.35
     căn
    0.35
     created
    0.35
     orchards
    0.34
     shipped
    0.34
    ppled
    0.34
     replicated
    0.34
    Create
    0.34
    POSITIVE LOGITS
    疳
    0.50
    Nicht
    0.48
    それが
    0.44
    缑
    0.44
    ต้องการ
    0.44
    dimensioni
    0.44
    筁
    0.43
     Nicht
    0.43
    秕
    0.43
    מ
    0.43
    Activations Density 0.004%

    No Known Activations