© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 7380
    Prev
    Next
    INDEX
    Explanations

    prepositions and connecting phrases

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

    prepositions followed by specific topics

    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_53_width_65k_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
    :-)
    0.69
    いろいろ
    0.66
    BTW
    0.64
     mempunyai
    0.63
     IMHO
    0.63
     .....
    0.61
     advices
    0.60
     …..
    0.59
     :-
    0.59
     pptn
    0.59
    POSITIVE LOGITS
     unsurprisingly
    0.81
    Notably
    0.81
     subpar
    0.77
     underwhelming
    0.77
     incentiv
    0.75
     roughly
    0.75
     newfound
    0.75
    Alongside
    0.74
     굉장히
    0.73
     lauded
    0.73
    Activations Density 0.208%

    No Known Activations