© 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. 114711
    Prev
    Next
    INDEX
    Explanations

    office, audit, song

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

    both parties benefit

    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
     để
    0.51
     поможет
    0.51
     сможет
    0.50
    裱
    0.50
    可以使用
    0.49
     hoặc
    0.49
     असतील
    0.49
    ことができます
    0.49
     eğer
    0.48
     nếu
    0.48
    POSITIVE LOGITS
     rebound
    0.48
    9
    0.46
     compliance
    0.46
     الانت
    0.46
     risult
    0.45
     Prozent
    0.43
     dropped
    0.43
     rebounded
    0.42
     febru
    0.42
     násled
    0.42
    Activations Density 0.000%

    No Known Activations