© 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. 36773
    Prev
    Next
    INDEX
    Explanations

    contact with personal information

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

    numbers and punctuation

    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
    oa
    0.41
     کہنا
    0.40
    枴
    0.39
     οδη
    0.38
    uncul
    0.37
    readme
    0.37
     saying
    0.37
     ಮಾಡಿ
    0.37
    ongrass
    0.37
    puma
    0.36
    POSITIVE LOGITS
     CIE
    0.45
    𒊺
    0.45
    ޟ
    0.45
     obič
    0.45
     potenc
    0.43
     cerim
    0.42
    ሦ
    0.42
    𒋀
    0.42
    граф
    0.41
     tytu
    0.41
    Activations Density 0.000%

    No Known Activations