© 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. 210807
    Prev
    Next
    INDEX
    Explanations

    representing the population

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

    and increasingly, beyond

    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
     filmes
    0.50
    ات
    0.49
    碴
    0.49
    磨
    0.49
     séances
    0.47
     siamo
    0.46
     Berlín
    0.46
    无
    0.46
     pelo
    0.46
    డిన
    0.46
    POSITIVE LOGITS
    lastName
    0.50
    Vertices
    0.49
    (",")
    0.43
    мережа
    0.43
    vertices
    0.43
    ()))
    0.43
    rases
    0.43
     terk
    0.42
     верно
    0.42
    yra
    0.42
    Activations Density 0.000%

    No Known Activations