© 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. 620
    Prev
    Next
    INDEX
    Explanations

    code comments and keywords

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

    code comment or definition start

    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
     Гуляць
    0.30
    簟
    0.30
     amyloid
    0.29
     calcareous
    0.29
     OXIDES
    0.28
     Wastewater
    0.28
     সভাপত
    0.28
     Pogis
    0.28
     propylene
    0.28
     まま
    0.27
    POSITIVE LOGITS
    //
    0.75
    /*
    0.67
    /**
    0.66
    var
    0.64
    const
    0.63
    if
    0.63
    ///
    0.61
    ////////////////
    0.59
    ////
    0.58
    let
    0.58
    Activations Density 0.001%

    No Known Activations