© 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. 16370
    Prev
    Next
    INDEX
    Explanations

    numbers as ages

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

    ages and associated 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
    學生
    0.47
    嚗
    0.47
     হইয়াছিলেন
    0.45
     PP
    0.42
    Phys
    0.42
     করিয়
    0.42
     要
    0.42
     puedas
    0.42
     추출
    0.42
     pann
    0.42
    POSITIVE LOGITS
    ٫
    0.56
     წლის
    0.49
     businessman
    0.48
     jamás
    0.45
     býval
    0.45
    г
    0.42
     practitioner
    0.42
     statesman
    0.42
     egalitarian
    0.42
    businessman
    0.41
    Activations Density 0.024%

    No Known Activations