© 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. 4113
    Prev
    Next
    INDEX
    Explanations

    another thing

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

    describing difficulty or length

    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
    紝
    0.47
    来进行
    0.42
    带来的
    0.41
    済
    0.41
    並且
    0.38
    麥
    0.38
     আনুষ্ঠানিক
    0.38
     পরিমাণে
    0.38
    有一些
    0.38
    湡
    0.38
    POSITIVE LOGITS
     bloke
    0.90
     saddo
    0.79
     cunning
    0.79
     reckons
    0.77
     lads
    0.73
     dodgy
    0.71
     cheeky
    0.66
     remit
    0.64
     probs
    0.62
     shamb
    0.61
    Activations Density 0.137%

    No Known Activations