© 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. 10713
    Prev
    Next
    INDEX
    Explanations

    simply or just followed by a description

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

    the word "simply"

    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
     শুধুমাত্র
    0.52
    ⵏ
    0.49
     ४
    0.47
     ONLY
    0.47
     ३
    0.45
     nejen
    0.44
    ཎ
    0.43
    िकांत
    0.42
    RANGER
    0.42
     теркәлү
    0.41
    POSITIVE LOGITS
    u
    0.45
     simply
    0.43
    :
    0.41
     einfach
    0.40
    s
    0.39
    _
    0.38
    ifiably
    0.36
     unapolog
    0.36
    en
    0.35
    tolower
    0.35
    Activations Density 0.068%

    No Known Activations