© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 104637
    Prev
    Next
    INDEX
    Explanations

    mathematics and contact information

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.23
    。
    0.22
    名人
    0.21
    ENSE
    0.20
    <0xBC>
    0.20
    ITION
    0.20
    텔
    0.19
    。...
    0.19
    ICIO
    0.19
     Então
    0.19
    POSITIVE LOGITS
     perpendicular
    0.21
     Procedures
    0.19
    ዚህ
    0.19
     inactivation
    0.19
     Lactobacillus
    0.19
     posX
    0.19
     CuO
    0.19
     glPushMatrix
    0.18
     काळजी
    0.18
     পরিষ্কার
    0.18
    Activations Density 0.028%

    No Known Activations