© 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. 99885
    Prev
    Next
    INDEX
    Explanations

    `1-2, 3-4, 4 5, 12 13`

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

    lists of numbers and symbols

    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
    动力
    0.36
     milling
    0.34
    ండోత్సర్గము
    0.33
     .;
    0.31
    રોના
    0.31
    ప్రత్యర్థి
    0.31
    রদ্ব
    0.31
     冬
    0.31
     сопер
    0.30
     নয়াদ
    0.30
    POSITIVE LOGITS
    त्मा
    0.47
    ට
    0.46
     etiqu
    0.42
    दृ
    0.42
     yeni
    0.41
    lives
    0.41
     czyli
    0.40
    คือ
    0.40
     परिवर्त
    0.40
     Lives
    0.40
    Activations Density 0.009%

    No Known Activations