© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 38
    Prev
    Next
    INDEX
    Explanations

    so-called or also known as

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

    so-called

    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_53_width_65k_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
    ­
    0.49
     ….
    0.47
    
    0.46
     …
    0.45
    …</
    0.45
    <0xC2>
    0.43
     собственно
    0.43
     […]
    0.42
    …
    0.42
    </i>
    0.42
    POSITIVE LOGITS
     sogenannte
    0.65
     sogen
    0.64
     sogenannten
    0.60
     tzw
    0.60
     attrition
    0.59
    bracketing
    0.55
     buyout
    0.54
    所谓的
    0.53
    Attrition
    0.51
    deferred
    0.51
    Activations Density 0.499%

    No Known Activations