© 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. 132062
    Prev
    Next
    INDEX
    Explanations

    Kalyan Jewellers

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

    unique words, identifying or distinguishing

    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
     दहा
    0.52
    কারীদের
    0.51
    𝓼
    0.50
    旂
    0.50
    ി
    0.49
    सामान्य
    0.48
    亾
    0.48
    Baltimore
    0.47
    旛
    0.47
    डिशा
    0.47
    POSITIVE LOGITS
     docket
    0.41
    rys
    0.39
     responsible
    0.39
     خونه
    0.39
     mutually
    0.38
    topics
    0.38
    jati
    0.38
    irian
    0.38
    body
    0.38
     attach
    0.38
    Activations Density 0.000%

    No Known Activations