© 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. 126451
    Prev
    Next
    INDEX
    Explanations

    appeared in or on

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

    verbs followed by prepositions

    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
     దీని
    0.53
     비슷한
    0.44
    ૧
    0.43
     오늘도
    0.42
     extrapolate
    0.42
     disband
    0.42
    ющих
    0.41
     mínimo
    0.41
     painfully
    0.41
     ナイス
    0.41
    POSITIVE LOGITS
    =
    0.43
    aling
    0.42
     Ln
    0.42
    mer
    0.41
    ای
    0.41
     Courts
    0.41
     =
    0.41
    ニューヨーク
    0.40
     Well
    0.40
     New
    0.40
    Activations Density 0.002%

    No Known Activations