© 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. 35472
    Prev
    Next
    INDEX
    Explanations

    Te, p, h, σ, c, n, 1

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

    mathematical variables and expressions

    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
     योजना
    0.50
    Botan
    0.50
    ཎ
    0.50
     pecados
    0.49
    gå
    0.49
    ér
    0.48
     फैलाने
    0.47
    zinha
    0.47
     расходы
    0.47
    ambahkan
    0.46
    POSITIVE LOGITS
    (),
    0.56
    ()
    0.55
    ，
    0.51
     environnement
    0.51
    時の
    0.50
     on
    0.49
     arisen
    0.48
    ("")
    0.47
    、
    0.47
     invariants
    0.47
    Activations Density 0.004%

    No Known Activations