© 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. 164548
    Prev
    Next
    INDEX
    Explanations

    allows, not, can, found, and

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

    preventing imitation

    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
    ात
    0.50
     اص
    0.47
     由
    0.46
     関
    0.46
     확실
    0.46
     马
    0.44
     गत
    0.44
    عا
    0.43
    ᆹ
    0.43
     drive
    0.42
    POSITIVE LOGITS
     appli
    0.50
     wys
    0.46
     upto
    0.46
    および
    0.46
     poplar
    0.45
     newsp
    0.44
    upam
    0.44
     and
    0.43
     ਅਤੇ
    0.43
    新技术
    0.42
    Activations Density 0.001%

    No Known Activations