© 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. 9729
    Prev
    Next
    INDEX
    Explanations

    many, millions, plenty, numerous

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

    many different possibilities

    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
    يدك
    0.29
    垐
    0.27
    ifications
    0.25
     ederek
    0.25
    ('/',
    0.24
    ของเรา
    0.24
    기로
    0.23
    作用
    0.23
    ("/",
    0.23
    தும்
    0.23
    POSITIVE LOGITS
     many
    0.33
     muchos
    0.32
     much
    0.31
     beaucoup
    0.31
     viele
    0.30
     birçok
    0.29
     mnoho
    0.29
     plenty
    0.28
     العديد
    0.28
     даже
    0.28
    Activations Density 0.280%

    No Known Activations