© 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. 211025
    Prev
    Next
    INDEX
    Explanations

    future financial investments

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

    quantity number turns position first

    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
    ר
    0.52
    specifically
    0.51
    ема
    0.48
     specifically
    0.47
    ر
    0.44
    squiggle
    0.43
    ्‍य
    0.42
     ممال
    0.42
     보이
    0.42
     dupa
    0.41
    POSITIVE LOGITS
     Ressourcen
    0.53
     vogliamo
    0.50
     fosse
    0.46
    氇
    0.46
    engah
    0.45
     déclaration
    0.44
     pilotes
    0.43
     degré
    0.43
    ü
    0.43
    ോഷ്യ
    0.42
    Activations Density 0.001%

    No Known Activations