© 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. 72946
    Prev
    Next
    INDEX
    Explanations

    breaking into, appearing, becoming

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

    can followed by verbs/outcomes

    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
     consists
    0.46
    :
    0.43
    是一名
    0.42
     Game
    0.42
     Abby
    0.40
     Case
    0.39
     Nel
    0.39
    @
    0.39
     intends
    0.38
     Sinatra
    0.38
    POSITIVE LOGITS
    變成
    0.54
     превра
    0.54
    变成
    0.52
     вдруг
    0.50
    忽然
    0.50
    居然
    0.49
     plötzlich
    0.47
    变成了
    0.46
    竟然
    0.45
    变为
    0.45
    Activations Density 0.122%

    No Known Activations