© 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. 154940
    Prev
    Next
    INDEX
    Explanations

    Son of, whom I, exterior grade

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

    advice and considerations

    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
    ad
    0.57
    ord
    0.57
    om
    0.55
    ur
    0.54
    f
    0.54
    id
    0.52
    ht
    0.52
    io
    0.52
    ol
    0.51
    ut
    0.51
    POSITIVE LOGITS
     permiso
    0.53
     catégorie
    0.53
     échange
    0.51
     pequeña
    0.48
     izin
    0.47
     ganas
    0.47
     barrios
    0.46
     licencia
    0.46
    تبع
    0.46
     traduc
    0.45
    Activations Density 0.011%

    No Known Activations