© 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. 3719
    Prev
    Next
    INDEX
    Explanations

    states of being and modifiers

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

    prepositions connecting concepts

    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
     क्योंकि
    0.47
     защото
    0.44
     omdat
    0.43
    .*
    0.43
     ذریع
    0.43
     perquè
    0.43
    ।...
    0.42
    。
    0.42
     کیونکہ
    0.42
    Jeśli
    0.41
    POSITIVE LOGITS
     is
    0.54
     this
    0.46
     είναι
    0.46
     are
    0.45
     will
    0.41
     adalah
    0.39
     buvo
    0.39
     fluctuates
    0.39
     dieser
    0.39
     may
    0.38
    Activations Density 0.597%

    No Known Activations