© 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. 163910
    Prev
    Next
    INDEX
    Explanations

    daily breakfast, very long, is consistent

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

    dangerous, significance, truly, alleys

    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
     incentives
    0.53
     barges
    0.51
     zippers
    0.46
     microphones
    0.46
    纮
    0.46
    िवर्स
    0.46
    omorphisms
    0.44
    ർഷ
    0.44
    ৃঙ্খলা
    0.44
     funerals
    0.44
    POSITIVE LOGITS
    nil
    0.52
    leşik
    0.52
    netje
    0.51
    !
    0.51
     chart
    0.51
     любые
    0.50
    até
    0.50
     aplicando
    0.49
     kancel
    0.49
     takım
    0.48
    Activations Density 0.000%

    No Known Activations